Feature learning is decoupled from generalization in high capacity neural networks | Paper Citation Record

Observation a0e59c41-770d-4f7d-951f-88d18a6a2832 · outbound

This paper cites The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks.

Feature learning is decoupled from generalization in high capacity neural networks The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.001723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f23fbd5f-4ecc-495d-830b-22d5bfef3a06 · outbound

This paper cites Aiudi, R.

Feature learning is decoupled from generalization in high capacity neural networks Aiudi, R

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.006053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215ebcff-3b9b-41cd-af18-ba2f9a88e71a · outbound

This paper cites Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods.

Feature learning is decoupled from generalization in high capacity neural networks Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:38.139347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 26f6ad5b-063e-44cc-817b-25645fb36788 · outbound

This paper cites What Can ResNet Learn Efficiently, Going Beyond Kernels?.

Feature learning is decoupled from generalization in high capacity neural networks What Can ResNet Learn Efficiently, Going Beyond Kernels?

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.014664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c29254af-3f9c-49ba-90a1-6d36a13844e5 · outbound

This paper cites Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) Learning.

Feature learning is decoupled from generalization in high capacity neural networks Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.019292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b09f77b0-957d-4be2-b64f-50b9328f696a · outbound

This paper cites Linear Algebraic Structure of Word Senses, with Applications to Polysemy.

Feature learning is decoupled from generalization in high capacity neural networks Linear Algebraic Structure of Word Senses, with Applications to Polysemy

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.023904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d76cbb8c-d03f-4d7c-9570-21605a0d12f2 · outbound

This paper cites A Closer Look at Memorization in Deep Networks.

Feature learning is decoupled from generalization in high capacity neural networks A Closer Look at Memorization in Deep Networks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.028075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf62f218-02a6-4072-814a-1f2f5f07d01f · outbound

This paper cites The Optimization Landscape of SGD Across the Feature Learning Strength.

Feature learning is decoupled from generalization in high capacity neural networks The Optimization Landscape of SGD Across the Feature Learning Strength

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.032569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03b9d682-2d1d-483a-9bdf-29eac526326d · outbound

This paper cites Frequency bias in neural networks for input of non-uniform density.

Feature learning is decoupled from generalization in high capacity neural networks Frequency bias in neural networks for input of non-uniform density

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:41.517191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8f97ebed-f8ec-4f8c-af1d-9596aadbbe02 · outbound

This paper cites Spectrum dependent learning curves in kernel regression and wide neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Spectrum dependent learning curves in kernel regression and wide neural networks

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:41.351332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f8d0242f-3bae-4a32-992b-7f413e25c6c9 · outbound

This paper cites How Feature Learning Can Improve Neural Scaling Laws.

Feature learning is decoupled from generalization in high capacity neural networks How Feature Learning Can Improve Neural Scaling Laws

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.808219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 92e7617d-8833-443b-a5bb-1d5b3e0d1490 · outbound

This paper cites Language models are few-shot learners.

Feature learning is decoupled from generalization in high capacity neural networks Language models are few-shot learners

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.047386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb472d65-e66c-44c2-b7e7-12bb13d1d036 · outbound

This paper cites A kernel analysis of feature learning in deep neural networks.

Feature learning is decoupled from generalization in high capacity neural networks A kernel analysis of feature learning in deep neural networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.051053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f814fb89-ea8b-4626-b190-7fb15ee5aedf · outbound

This paper cites Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.054608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde4bf20-aa6d-462c-a3f1-84dde0c4d658 · outbound

This paper cites On Lazy Training in Differentiable Programming.

Feature learning is decoupled from generalization in high capacity neural networks On Lazy Training in Differentiable Programming

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.058057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc8dba36-0106-4584-935e-7b99202f6054 · outbound

This paper cites Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective.

Feature learning is decoupled from generalization in high capacity neural networks Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.969198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a8fea7c1-cb6b-4a1d-a376-59941a79baec · outbound

This paper cites Neural Networks can Learn Representations with Gradient Descent.

Feature learning is decoupled from generalization in high capacity neural networks Neural Networks can Learn Representations with Gradient Descent

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.064891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 531c56ec-4101-422c-91e9-5226da84e9bf · outbound

This paper cites Learning parities with neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Learning parities with neural networks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:41.140043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 912eaccd-4bb1-4b41-b64f-11e825bebde8 · outbound

This paper cites From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks.

Feature learning is decoupled from generalization in high capacity neural networks From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.071621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d53e79a8-c90d-4458-accc-b28d341301ff · outbound

This paper cites How rotational invariance of common kernels prevents generalization in high dimensions.

Feature learning is decoupled from generalization in high capacity neural networks How rotational invariance of common kernels prevents generalization in high dimensions

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:40.909044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7646d6e3-5639-4180-beb3-c2e60f38db05 · outbound

This paper cites Toy Models of Superposition.

Feature learning is decoupled from generalization in high capacity neural networks Toy Models of Superposition

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.078613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1af5ec08-b7dd-43b3-acae-d35d9369cca7 · outbound

This paper cites Scaling Exponents Across Parameterizations and Optimizers.

Feature learning is decoupled from generalization in high capacity neural networks Scaling Exponents Across Parameterizations and Optimizers

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.081920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13c27667-5119-417a-a95d-b883c7d848fa · outbound

This paper cites Critical feature learning in deep neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Critical feature learning in deep neural networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.085319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 246f93e5-70a6-4b46-a474-5d70265b7ea3 · outbound

This paper cites Random feature ampliﬁcation: Feature learning and generalization in neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Random feature ampliﬁcation: Feature learning and generalization in neural networks

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:40.741860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a3a0aed8-e6bf-4214-9fb7-f7ddc5906804 · outbound

This paper cites On the Implicit Bias Towards Minimal Depth of Deep Neural Networks.

Feature learning is decoupled from generalization in high capacity neural networks On the Implicit Bias Towards Minimal Depth of Deep Neural Networks

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.762133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ba78a3c7-f7eb-4111-bedb-592dac8181e2 · outbound

This paper cites On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels.

Feature learning is decoupled from generalization in high capacity neural networks On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.751175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a3a44a7b-845b-4e4e-b7db-0c772e632703 · outbound

This paper cites Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum.

Feature learning is decoupled from generalization in high capacity neural networks Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.738925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b865dea3-69dd-41b7-a0ac-7f377d5d5f08 · outbound

This paper cites Disentangling feature and lazy training in deep neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Disentangling feature and lazy training in deep neural networks

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.928319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 56288377-77f8-468f-8489-79d1735c94db · outbound

This paper cites When do neural networks outperform kernel methods? In Advances in Neural Information Processing Systems, volume 33, page 14820–14830.

Feature learning is decoupled from generalization in high capacity neural networks When do neural networks outperform kernel methods? In Advances in Neural Information Processing Systems, volume 33, page 14820–14830

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:40.535237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 28ae4097-2800-4b92-ba9b-1011070948aa · outbound

This paper cites Limitations of Neural Collapse for Understanding Generalization in Deep Learning.

Feature learning is decoupled from generalization in high capacity neural networks Limitations of Neural Collapse for Understanding Generalization in Deep Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.110654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b410276-89de-456a-a04c-c31374e792b5 · outbound

This paper cites Mathematical Models of Computation in Superposition.

Feature learning is decoupled from generalization in high capacity neural networks Mathematical Models of Computation in Superposition

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.115036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3764a69c-3cfa-4d83-9e73-06e62b01ad77 · outbound

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

Feature learning is decoupled from generalization in high capacity neural networks Neural tangent kernel: Convergence and generalization in neural networks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:40.347764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7bbf47d7-0c8f-456b-86ea-79b753d28159 · outbound

This paper cites Highly accurate protein structure prediction with alphafold.

Feature learning is decoupled from generalization in high capacity neural networks Highly accurate protein structure prediction with alphafold

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.122585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc9c924-79bd-41dd-ba7f-274bc8dc420c · outbound

This paper cites The lazy (NTK) and rich ($\mu$P) regimes: a gentle tutorial.

Feature learning is decoupled from generalization in high capacity neural networks The lazy (NTK) and rich ($\mu$P) regimes: a gentle tutorial

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.126047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 146a10a5-e4c7-4103-ae94-635abcc860ed · outbound

This paper cites Similarity of Neural Network Representations Revisited.

Feature learning is decoupled from generalization in high capacity neural networks Similarity of Neural Network Representations Revisited

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.129479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e1369d-40ec-478c-82bf-94d7d5869042 · outbound

This paper cites Neural Collapse: A Review on Modelling Principles and Generalization.

Feature learning is decoupled from generalization in high capacity neural networks Neural Collapse: A Review on Modelling Principles and Generalization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.133481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef157b4-f3a6-479c-a172-f49b83b1d175 · outbound

This paper cites Deep learning.

Feature learning is decoupled from generalization in high capacity neural networks Deep learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.136671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e24baa8-8072-47d9-8375-c7361d51d3e1 · outbound

This paper cites Deep Neural Networks as Gaussian Processes.

Feature learning is decoupled from generalization in high capacity neural networks Deep Neural Networks as Gaussian Processes

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.139654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5ec147e-af05-42d5-816c-2628dc1b0be0 · outbound

This paper cites Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK.

Feature learning is decoupled from generalization in high capacity neural networks Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.143199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ab219f1-b177-4de1-918e-9cb3a955493a · outbound

This paper cites Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking.

Feature learning is decoupled from generalization in high capacity neural networks Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.147161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9051f66-5ab2-403d-87e1-9678921a5d5e · outbound

This paper cites Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels.

Feature learning is decoupled from generalization in high capacity neural networks Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.681522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8f03c7ec-f29c-4258-b148-aa80e0eb1e03 · outbound

This paper cites Implicit bias in deep linear classification: Initialization scale vs training accuracy.

Feature learning is decoupled from generalization in high capacity neural networks Implicit bias in deep linear classification: Initialization scale vs training accuracy

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:40.180210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 26c5b5d2-13d6-4a2b-98c7-8d718e59c47f · outbound

This paper cites Neural networks efficiently learn low-dimensional representations with sgd.

Feature learning is decoupled from generalization in high capacity neural networks Neural networks efficiently learn low-dimensional representations with sgd

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:40.024255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 76038ca5-b51d-486f-9a90-54834a59fc4f · outbound

This paper cites Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics.

Feature learning is decoupled from generalization in high capacity neural networks Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.159912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e080e7b4-c1f3-449a-a7e0-3a6276f849cf · outbound

This paper cites Visualising feature learning in deep neural networks by diagonalizing the forward feature map.

Feature learning is decoupled from generalization in high capacity neural networks Visualising feature learning in deep neural networks by diagonalizing the forward feature map

Reference 45

Resolution: verified exact; doi, observed 2026-08-06T14:17:37.662418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0ba14e3f-0156-4630-852f-482165cf09dc · outbound

This paper cites A self consistent theory of gaussian processes captures feature learning effects in finite cnns.

Feature learning is decoupled from generalization in high capacity neural networks A self consistent theory of gaussian processes captures feature learning effects in finite cnns

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:39.781774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a725812b-ecf4-4c62-a210-2b2029872e46 · outbound

This paper cites Alemi, Jascha Sohl-Dickstein, and Samuel S.

Feature learning is decoupled from generalization in high capacity neural networks Alemi, Jascha Sohl-Dickstein, and Samuel S

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:39.569805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eb40b16e-1aec-46e2-a36b-2899ec97533c · outbound

This paper cites Schoenholz.

Feature learning is decoupled from generalization in high capacity neural networks Schoenholz

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:39.402320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2914d680-3b47-419e-9358-13fe943e03a8 · outbound

This paper cites Feature visualization.

Feature learning is decoupled from generalization in high capacity neural networks Feature visualization

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.176258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 385df943-c7d1-40ea-9711-e466110557f5 · outbound

This paper cites What can linearized neural networks actually say about generalization?.

Feature learning is decoupled from generalization in high capacity neural networks What can linearized neural networks actually say about generalization?

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.179898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c767e82-b8fc-40e7-bc92-e3eed480adf3 · outbound

This paper cites Prevalence of Neural Collapse during the terminal phase of deep learning training.

Feature learning is decoupled from generalization in high capacity neural networks Prevalence of Neural Collapse during the terminal phase of deep learning training

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.183370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdf39048-1f06-4a38-872a-1590a0dc01e4 · outbound

This paper cites Learning sparse features can lead to overfitting in neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Learning sparse features can lead to overfitting in neural networks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.186905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b68433be-c47f-44d5-b1d0-f390fdacc10a · outbound

This paper cites On the spectral bias of neural networks.

Feature learning is decoupled from generalization in high capacity neural networks On the spectral bias of neural networks

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:39.172776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6940197f-a7b6-4a1d-82a7-3a7610951614 · outbound

This paper cites Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed.

Feature learning is decoupled from generalization in high capacity neural networks Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.581135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation be64cf14-2496-4447-953a-dffb0db11d89 · outbound

This paper cites Analyzing finite neural networks: Can we trust neural tangent kernel theory?.

Feature learning is decoupled from generalization in high capacity neural networks Analyzing finite neural networks: Can we trust neural tangent kernel theory?

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:38.995024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a5e63c65-cde8-4c1b-b84c-98a24efe1a3b · outbound

This paper cites Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs.

Feature learning is decoupled from generalization in high capacity neural networks Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.201402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af256f2f-4684-4dc6-9b86-269b8e958115 · outbound

This paper cites Separation of scales and a thermodynamic description of feature learning in some cnns.

Feature learning is decoupled from generalization in high capacity neural networks Separation of scales and a thermodynamic description of feature learning in some cnns

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.204996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5dc8c5-2d2a-4888-aad6-f1915755851c · outbound

This paper cites A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features.

Feature learning is decoupled from generalization in high capacity neural networks A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features

Reference 58

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.553585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5e159d8c-0aad-42b2-b8a6-f655c4ae8a82 · outbound

This paper cites Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm.

Feature learning is decoupled from generalization in high capacity neural networks Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.869152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a941fc44-d26b-4c11-9991-fa5cb3f08abe · outbound

This paper cites Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks.

Feature learning is decoupled from generalization in high capacity neural networks Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.215595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 654be64e-9764-4cf3-b74b-43ed9d71f90d · outbound

This paper cites Feature selection and low test error in shallow low-rotation relu networks.

Feature learning is decoupled from generalization in high capacity neural networks Feature selection and low test error in shallow low-rotation relu networks

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:38.845389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 889f29ad-b041-435d-a841-2fa2fc15675d · outbound

This paper cites Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data.

Feature learning is decoupled from generalization in high capacity neural networks Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data

Reference 62

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T14:17:37.541736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b6e347f-1e27-4575-a616-1fa15168b497 · outbound

This paper cites Fundamental computational limits of weak learnability in high-dimensional multi-index models.

Feature learning is decoupled from generalization in high capacity neural networks Fundamental computational limits of weak learnability in high-dimensional multi-index models

Reference 63

Resolution: verified exact; doi, observed 2026-08-06T14:17:37.527764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 372fb401-64c8-455d-9e95-69da73a91855 · outbound

This paper cites Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes.

Feature learning is decoupled from generalization in high capacity neural networks Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:17:37.352664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2bdd98f0-9d2a-4d3b-956b-480b6a9697d8 · outbound

This paper cites Limitations of the NTK for Understanding Generalization in Deep Learning.

Feature learning is decoupled from generalization in high capacity neural networks Limitations of the NTK for Understanding Generalization in Deep Learning

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.234144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13bad243-2c1c-4a16-b8fe-04409858a5f8 · outbound

This paper cites Beyond Lazy Training for Over-parameterized Tensor Decomposition.

Feature learning is decoupled from generalization in high capacity neural networks Beyond Lazy Training for Over-parameterized Tensor Decomposition

Reference 66

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T14:17:37.329712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5764a9b1-07fc-4849-bd0c-c33aac7729cf · outbound

This paper cites More than a toy: Random matrix models predict how real-world neural representations generalize.

Feature learning is decoupled from generalization in high capacity neural networks More than a toy: Random matrix models predict how real-world neural representations generalize

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:38.656933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ef8c8e6e-cb06-427a-b578-23767bcd07da · outbound

This paper cites Regularization matters: Generalization and optimization of neural nets v.s.

Feature learning is decoupled from generalization in high capacity neural networks Regularization matters: Generalization and optimization of neural nets v.s

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:17:38.495149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4f56b5ce-177c-40c5-bed5-5433383538a8 · outbound

This paper cites On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective.

Feature learning is decoupled from generalization in high capacity neural networks On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.249270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aeb6ab2-def9-47aa-970f-0b5d7a180284 · outbound

This paper cites an unresolved cited work.

Feature learning is decoupled from generalization in high capacity neural networks Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-06T14:17:38.312426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cee354a0-a4a9-4536-9824-796fe7941253 · outbound

This paper cites On the Power and Limitations of Random Features for Understanding Neural Networks.

Feature learning is decoupled from generalization in high capacity neural networks On the Power and Limitations of Random Features for Understanding Neural Networks

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.255620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7b8b28c-dfa2-4da3-8511-043710d2d55e · outbound

This paper cites Wide Residual Networks.

Feature learning is decoupled from generalization in high capacity neural networks Wide Residual Networks

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.258687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e91c8c6b-dba0-4203-bf23-fc0aca4c58ef · outbound

This paper cites Understanding deep learning requires rethinking generalization.

Feature learning is decoupled from generalization in high capacity neural networks Understanding deep learning requires rethinking generalization

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T14:17:37.261961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers