Paper Citation Record · LEDGER

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

As of 19 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 5 inbound Pith citation observations for arXiv:2504.18208.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.18208 v2

Coverage vector

measured 94 of 94 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:35:07.689364Z

measured 99 of 99 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T06:04:02.505287Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-30T19:55:01.085125Z

Reference resolution

94 of 94 outbound references displayed

verified exact1
verified fuzzy69
unresolved22
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 43c8d84a-ddbb-428b-a381-c984c82433f5 · outbound

This paper cites A convergence theory for deep learning via over-parameterization.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime A convergence theory for deep learning via over-parameterization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.327201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af8302f8-7f7f-4c76-9e2e-460ac259b5f0 · outbound

This paper cites Gradient flows: in metric spaces and in the space of probability measures.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Gradient flows: in metric spaces and in the space of probability measures

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.331601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f3f7b2-7c55-477b-8303-89e4ac102fec · outbound

This paper cites an unresolved cited work.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.335445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e42f21-edbd-441f-938a-01d0049d281d · outbound

This paper cites Maximum mean discrepancy gradient flow.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Maximum mean discrepancy gradient flow

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.339368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a9a907-4570-4a8f-b47b-395d1cad14b2 · outbound

This paper cites Breaking the curse of dimensionality with convex neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Breaking the curse of dimensionality with convex neural networks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.343221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba05473-12e8-4ec2-84f1-e29fd8a8382f · outbound

This paper cites Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.347184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c2d240-ba6d-4709-93e4-f189296b3431 · outbound

This paper cites Multiple kernel learning, conic duality, and the SMO algorithm.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Multiple kernel learning, conic duality, and the SMO algorithm

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.351646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c49d363-2981-4599-adbc-cceee9a6d60d · outbound

This paper cites On global convergence of ResNets: From finite to infinite width using linear parameterization.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On global convergence of ResNets: From finite to infinite width using linear parameterization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.355445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1312402-b2b1-4671-baa6-51b3284792fc · outbound

This paper cites Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.359299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa46ae12-ca97-4ee4-a363-ec46c83010b7 · outbound

This paper cites Modern regularization methods for inverse problems.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Modern regularization methods for inverse problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.363639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cea5307-7035-4f56-8210-ed291b3d441f · outbound

This paper cites Learning time-scales in two-layers neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Learning time-scales in two-layers neural networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.367499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c2c8f5a-eb89-400c-834a-71dd3c2e2532 · outbound

This paper cites On Learning Gaussian Multi-index Models with Gradient Flow.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On Learning Gaussian Multi-index Models with Gradient Flow

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.371474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc7132a-0975-4ef3-94da-5afc065aba35 · outbound

This paper cites Stochastic approximation: a dynamical systems viewpoint.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Stochastic approximation: a dynamical systems viewpoint

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.375645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0400c10-ecaf-44d7-9672-603451ed5597 · outbound

This paper cites Stochastic approximation with two time scales.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Stochastic approximation with two time scales

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.379486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3a16b8-7c41-49e1-aed5-69ceca25e65a · outbound

This paper cites Optimization methods for large-scale machine learning.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Optimization methods for large-scale machine learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.383788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855b6961-4784-4bc4-a3dd-4a8729a7ceee · outbound

This paper cites On the global convergence of Wasserstein gradient flow of the Coulomb discrepancy.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On the global convergence of Wasserstein gradient flow of the Coulomb discrepancy

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.388607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e206f2e-96a7-4c32-8454-e6ace54bbecf · outbound

This paper cites Quantization of Measures and Gradient Flows: a Perturbative Approach in the 2-Dimensional Case.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Quantization of Measures and Gradient Flows: a Perturbative Approach in the 2-Dimensional Case

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-16T10:35:07.808148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dff33a19-076b-4504-9c7d-626bceb54753 · outbound

This paper cites (De)-regularized Maximum Mean Discrepancy Gradient Flow.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime (De)-regularized Maximum Mean Discrepancy Gradient Flow

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.396185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ed5625-643a-45a5-880b-c52e85306d2f · outbound

This paper cites Analysis of langevin monte carlo from poincare to log-sobolev.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Analysis of langevin monte carlo from poincare to log-sobolev

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.399853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67cfadc8-c3b6-4569-8d8a-df5313d741a8 · outbound

This paper cites SVGD as a kernelized Wasserstein gradient flow of the chi-squared diver- gence.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime SVGD as a kernelized Wasserstein gradient flow of the chi-squared diver- gence

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.403617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a7398c6-0fc6-4a7f-8f74-1c3f5994871f · outbound

This paper cites Mean-Field Langevin Dynamics: Exponential Convergence and Annealing.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mean-Field Langevin Dynamics: Exponential Convergence and Annealing

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.781067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ff209de8-3bcc-464c-9462-4be7fa626d91 · outbound

This paper cites On Lazy Training in Differentiable Pro- gramming.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On Lazy Training in Differentiable Pro- gramming

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.768816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6cad4cfd-c76c-4b77-8a29-2f94636d71d3 · outbound

This paper cites On the Global Convergence of Gradient Descent for Over- parameterized Models using Optimal Transport.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On the Global Convergence of Gradient Descent for Over- parameterized Models using Optimal Transport

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.756748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8333ab3d-e1c4-4f60-8aab-64f81c22d1cb · outbound

This paper cites Approximation by superpositions of a sigmoidal function.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Approximation by superpositions of a sigmoidal function

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.418212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db6a92df-79e1-4424-b247-f3d7a55d7b83 · outbound

This paper cites Exact reconstruction using Beurling minimal ex- trapolation.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Exact reconstruction using Beurling minimal ex- trapolation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.738200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 841dc573-15d0-4049-93b1-422fe9174208 · outbound

This paper cites High-dimensional data analysis: The curses and blessings of dimen- sionality.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime High-dimensional data analysis: The curses and blessings of dimen- sionality

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.727753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fd6f6990-ef30-4bd0-adc7-f6fa1df90205 · outbound

This paper cites Gradient descent finds global minima of deep neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Gradient descent finds global minima of deep neural networks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.716819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 70e46147-6316-4327-b4cf-d280160e4282 · outbound

This paper cites Exact support recovery for sparse spikes deconvolution.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Exact support recovery for sparse spikes deconvolution

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.705379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 52c82066-5453-4c7f-9fe7-7f84da4c1c45 · outbound

This paper cites On the rate of convergence in Wasserstein distance of the empirical measure.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On the rate of convergence in Wasserstein distance of the empirical measure

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.693924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d94f6a5c-b8ac-45b3-aca2-eede52f97123 · outbound

This paper cites Global convergence in training large-scale transformers.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Global convergence in training large-scale transformers

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.681588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 70195d83-b7ea-42c4-bbbb-f76069189c68 · outbound

This paper cites When do neural networks outperform kernel methods?.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime When do neural networks outperform kernel methods?

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.670087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bd5aa5cf-2e7d-473a-99ae-138d353ea47b · outbound

This paper cites KALE flow: A relaxed KL gradient flow for probabilities with disjoint support.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime KALE flow: A relaxed KL gradient flow for probabilities with disjoint support

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.658045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bbf6f600-518f-432a-83e6-37a870676ed6 · outbound

This paper cites Separable nonlinear least squares: the variable projection method and its applications.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Separable nonlinear least squares: the variable projection method and its applications

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.644291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 95a47204-1407-471b-9341-46657ed91a66 · outbound

This paper cites The differentiation of pseudo-inverses and nonlinear least squares problems whose variables separate.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime The differentiation of pseudo-inverses and nonlinear least squares problems whose variables separate

Reference 34

Resolution: malformed identifier; raw_fallback, observed 2026-08-16T10:35:08.632692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dd835aff-7ccc-4e58-b891-61340e6fd779 · outbound

This paper cites Deep Learning.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Deep Learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.621414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c791fc03-04ba-4da0-ac7f-0a5184e42e5b · outbound

This paper cites A kernel two-sample test.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime A kernel two-sample test

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.609644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 56477777-4d41-4520-839d-5607d8bd3dcc · outbound

This paper cites Shampoo: Preconditioned stochastic tensor optimization.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Shampoo: Preconditioned stochastic tensor optimization

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.597707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 03311575-1a82-4ed7-b77f-8ac6cedf3ded · outbound

This paper cites Ordinary differential equations.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Ordinary differential equations

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.473822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130ba544-5796-4a29-b037-49485d8e0cad · outbound

This paper cites Deep residual learning for image recognition.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Deep residual learning for image recognition

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.575716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d7cfa46c-5914-4c2d-ac26-aaca7e475a08 · outbound

This paper cites Generative Sliced MMD Flows with Riesz Kernels.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Generative Sliced MMD Flows with Riesz Kernels

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.564294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1fdf15e9-c590-4f91-bf5b-6691a359d317 · outbound

This paper cites Wasserstein gradient flows of the discrepancy with distance kernel on the line.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Wasserstein gradient flows of the discrepancy with distance kernel on the line

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.551132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1a27aad9-9fcc-4bf5-b6cb-19973e7e515c · outbound

This paper cites Wasserstein steepest descent flows of discrepancies with Riesz ker- nels.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Wasserstein steepest descent flows of discrepancies with Riesz ker- nels

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.538519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 113e99b3-790c-40ee-bb77-25d140cded28 · outbound

This paper cites ODEPACK, a systemized collection of ODE solvers.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime ODEPACK, a systemized collection of ODE solvers

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.526539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d122c635-f9f3-4494-afa5-eb33601b47db · outbound

This paper cites Kernel methods in machine learning.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Kernel methods in machine learning

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.513034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83363099-aa87-40b3-a46e-a819b317fd5a · outbound

This paper cites Mean-field Langevin dynamics and energy landscape of neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mean-field Langevin dynamics and energy landscape of neural networks

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.499043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 968b916d-1e30-4574-85e1-2bdd5318e50f · outbound

This paper cites Asymptotic analysis for a very fast diffusion equation arising from the 1D quantization problem.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Asymptotic analysis for a very fast diffusion equation arising from the 1D quantization problem

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.485512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3944f926-b318-4e72-be94-589c56a512f5 · outbound

This paper cites Weighted ultrafast diffusion equations: from well-posedness to long-time behaviour.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Weighted ultrafast diffusion equations: from well-posedness to long-time behaviour

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.473408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f702c31b-0e03-4da6-afe0-ff10bcdead05 · outbound

This paper cites A note on convergence of solu- tions of total variation regularized linear inverse problems.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime A note on convergence of solu- tions of total variation regularized linear inverse problems

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.461701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ed7981e3-2b6e-4a60-81ec-26e942282705 · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Neural tangent kernel: Convergence and generalization in neural networks

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.450155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 02e28904-395b-4f75-8938-1eedb6c7f931 · outbound

This paper cites The variational formulation of the Fokker–Planck equation.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime The variational formulation of the Fokker–Planck equation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.437018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 60dbeb9e-e387-4da6-b687-223afdb3f42b · outbound

This paper cites Radial basis function neural network training using variable projection and fuzzy means.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Radial basis function neural network training using variable projection and fuzzy means

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.425070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3ccc1c67-2b08-487a-a756-45a8192ab7cf · outbound

This paper cites Learning multiple layers of features from tiny im- ages.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Learning multiple layers of features from tiny im- ages

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.413514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2e1c0806-579f-46f1-a586-05217f4fc044 · outbound

This paper cites Learning the kernel matrix with semidefinite programming.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Learning the kernel matrix with semidefinite programming

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.401583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5028a977-f57a-4f1e-8c14-542364e79a5c · outbound

This paper cites Wide neural networks of any depth evolve as linear models under gradient descent.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Wide neural networks of any depth evolve as linear models under gradient descent

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.386361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76339589-fd8f-49f6-8915-7a21b9633d30 · outbound

This paper cites Optimal entropy-transport prob- lems and a new Hellinger–Kantorovich distance between positive measures.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Optimal entropy-transport prob- lems and a new Hellinger–Kantorovich distance between positive measures

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.374069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2fb08b93-6058-4b87-8925-853dae03d768 · outbound

This paper cites On the linearity of large non-linear models: when and why the tangent kernel is constant.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime On the linearity of large non-linear models: when and why the tangent kernel is constant

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.361643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 14541fe5-765b-43c0-9d2b-f1829e01a933 · outbound

This paper cites Leveraging the two-timescale regime to demonstrate convergence of neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Leveraging the two-timescale regime to demonstrate convergence of neural networks

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.346724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 173241b4-afcb-4c06-8ce5-114c48d4c3d0 · outbound

This paper cites Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.335113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e62cbbc6-84a0-4d32-837a-3b90b7ae8ae4 · outbound

This paper cites Universal Kernels.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Universal Kernels

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.323034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b9d797a1-fb9c-4474-a556-6d9af415e119 · outbound

This paper cites Envelope theorems for arbitrary choice sets.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Envelope theorems for arbitrary choice sets

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.309707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3907dbe5-9522-4eba-9ae3-c1b81039796c · outbound

This paper cites Kernel mean embedding of distributions: A review and beyond.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Kernel mean embedding of distributions: A review and beyond

Reference 61

Resolution: malformed identifier; raw_fallback, observed 2026-08-16T10:35:08.294975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3aeaea96-7700-456d-9479-511aaadfa0c7 · outbound

This paper cites Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:07.572108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d578c376-bc6f-41bc-9478-2d46b0ef6cd7 · outbound

This paper cites Train like a (Var) Pro: Efficient training of neural networks with variable projection.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Train like a (Var) Pro: Efficient training of neural networks with variable projection

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.279066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d676dde-e413-4470-b262-2d5808102cc6 · outbound

This paper cites Convex analysis of the mean field langevin dynamics.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Convex analysis of the mean field langevin dynamics

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.266273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a900796e-1e0c-4916-9e5e-1e93f1e659f6 · outbound

This paper cites Separable least squares, variable projection, and the Gauss-Newton algorithm.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Separable least squares, variable projection, and the Gauss-Newton algorithm

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.253972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c43e0866-4b56-439d-81c1-db6bb0fc9a91 · outbound

This paper cites Stochastic processes and applications.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Stochastic processes and applications

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.242956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c0487041-6fea-45c7-bf52-91ec8ebbc026 · outbound

This paper cites An optimal Poincar´ e inequality for convex do- mains.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime An optimal Poincar´ e inequality for convex do- mains

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.232142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c0187158-cd7b-431a-9dc1-f3cc07d356c1 · outbound

This paper cites Variable projections neural network training.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Variable projections neural network training

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.221072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a14b27a1-3acd-4f7c-b6d7-dd4196ed960e · outbound

This paper cites Duality and stability in extremum problems involving convex functions.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Duality and stability in extremum problems involving convex functions

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.208399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 475649ef-f39a-4837-ae6a-9fb5425651db · outbound

This paper cites Integrals which are convex functionals.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Integrals which are convex functionals

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.196178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation edd5cc63-e611-453d-b8e9-d7a43ba25e34 · outbound

This paper cites Integrals which are convex functionals. II.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Integrals which are convex functionals. II

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.184693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a276b96f-a913-4fc7-b9ec-22d7ceb89d99 · outbound

This paper cites Global convergence of neuron birth-death dynamics.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Global convergence of neuron birth-death dynamics

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.173918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cd28db76-5b91-45dd-9f61-a1fd9f740fc0 · outbound

This paper cites A Course in the Calculus of Variations: Optimization, Regularity, and Modeling.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime A Course in the Calculus of Variations: Optimization, Regularity, and Modeling

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.162643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 155d3453-412f-4783-9caf-3f4b6cb585fc · outbound

This paper cites {Euclidean, metric, and Wasserstein} gradient flows: an overview.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime {Euclidean, metric, and Wasserstein} gradient flows: an overview

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.151424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 45f5b3d0-0937-4d6f-b3e8-761a9576fb28 · outbound

This paper cites Optimal transport for applied mathematicians.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Optimal transport for applied mathematicians

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.140736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 23f044b0-a27f-4d33-9859-b9dc218d2721 · outbound

This paper cites Learning with kernels: support vector machines, regularization, optimization, and beyond.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Learning with kernels: support vector machines, regularization, optimization, and beyond

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.129853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bd6521b1-dd81-4875-b098-67cbed6f7a8f · outbound

This paper cites Equivalence of distance-based and RKHS-based statistics in hypothesis testing.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Equivalence of distance-based and RKHS-based statistics in hypothesis testing

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.118507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d3e879b2-42e5-42a4-8bed-c5850c625000 · outbound

This paper cites Mean field analysis of neural networks: A central limit theorem.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mean field analysis of neural networks: A central limit theorem

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.107461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 172fa144-6266-4a13-9432-d479361960ad · outbound

This paper cites Separable non-linear least-squares minimization-possible improvements for neural net fitting.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Separable non-linear least-squares minimization-possible improvements for neural net fitting

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.095962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c6ad61f1-97eb-4d86-92b6-dc2851b9aef7 · outbound

This paper cites Universality, Char- acteristic Kernels and RKHS Embedding of Measures.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Universality, Char- acteristic Kernels and RKHS Embedding of Measures

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.085247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c8ea6bc-f248-402a-811c-5940b2da0737 · outbound

This paper cites Support vector machines.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Support vector machines

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.073897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c60b681-6673-4a64-85b8-dcd257919351 · outbound

This paper cites Mercer’s theorem on general domains: On the interaction between measures, kernels, and RKHSs.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mercer’s theorem on general domains: On the interaction between measures, kernels, and RKHSs

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.061846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2ba8fc1d-3810-4825-9b24-9bdb1a10ad22 · outbound

This paper cites Random Features Methods in Supervised Learning.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Random Features Methods in Supervised Learning

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.049529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3b4bbfaa-265c-4b59-b8d3-4dcb579eab48 · outbound

This paper cites Feature learning via mean-field langevin dynamics: classifying sparse parities and beyond.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Feature learning via mean-field langevin dynamics: classifying sparse parities and beyond

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.038214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55f53614-caf1-4b57-a219-c281c8635d65 · outbound

This paper cites Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.026763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b95774df-4dd7-4a94-a5ee-6b569b18829a · outbound

This paper cites Smoothing and decay estimates for nonlinear diffusion equations: equa- tions of porous medium type.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Smoothing and decay estimates for nonlinear diffusion equations: equa- tions of porous medium type

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.014235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dbebf28c-b926-452a-ba28-87a22883e409 · outbound

This paper cites The porous medium equation: mathematical theory.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime The porous medium equation: mathematical theory

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:08.001980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22a5ca96-f45b-4efc-b7b0-b1d3355f863b · outbound

This paper cites Partial optimization and Schur complement.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Partial optimization and Schur complement

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.990677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e14bef91-d744-478f-a048-e409767aba58 · outbound

This paper cites Optimal transport: old and new.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Optimal transport: old and new

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.978375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b03a16f9-c787-4847-a408-a89e6f01ef7a · outbound

This paper cites Mean-field langevin dynam- ics for signed measures via a bilevel approach.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Mean-field langevin dynam- ics for signed measures via a bilevel approach

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.964346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 49cd9bec-aa2f-4c8e-8491-a238719f9482 · outbound

This paper cites Tensor programs iv: Feature learning in infinite-width neural networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Tensor programs iv: Feature learning in infinite-width neural networks

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.952443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1435c61-be10-4513-8238-b43adac6039f · outbound

This paper cites Gradient descent optimizes over-parameterized deep ReLU networks.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime Gradient descent optimizes over-parameterized deep ReLU networks

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.940225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 11e3a01f-38f5-4156-9660-87aebf4a46b1 · outbound

This paper cites biased” quadratic regularization fb :t7→ 1 2t2 or the “unbiased.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime biased” quadratic regularization fb :t7→ 1 2t2 or the “unbiased

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.928225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8919791a-ee87-4a5e-b69f-b7a2273071c3 · outbound

This paper cites (50)) of width M∈{ 32, 128, 512, 1024}.

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime (50)) of width M∈{ 32, 128, 512, 1024}

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:35:07.916189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 2c071eb5-c3ce-4474-adad-e0b67ce530f9 · inbound

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures cites this paper.

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T06:04:02.505287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e6afbd-2b8b-4f40-bef8-226678459fb1 · inbound

Closed-Form Last Layer Optimization cites this paper.

Closed-Form Last Layer Optimization Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:01:13.465257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4d457766-2f47-4506-ad5a-0a628c2b9607 · inbound

Rethinking Neural Network Learning Rates: A Stackelberg Perspective cites this paper.

Rethinking Neural Network Learning Rates: A Stackelberg Perspective Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-19T14:43:06.662422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8a9fc212-4fed-4f96-90db-b4893dc3518d · inbound

Rethinking Neural Network Learning Rates: A Stackelberg Perspective cites this paper.

Rethinking Neural Network Learning Rates: A Stackelberg Perspective Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:55:01.087709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 426ea73a-23d6-4685-9315-7ced04b2844a · inbound

How are linear representations learned? Exact solutions to the dynamics of abstraction cites this paper.

How are linear representations learned? Exact solutions to the dynamics of abstraction Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T06:19:30.027337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.