Pith. sign in

Paper Citation Record · LEDGER

Effect of Activation Functions on the Training of Overparametrized Neural Nets

As of 15 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:1908.05660.

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

pith.paper-citation-record.v1
1908.05660 v4

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T13:02:29.815116Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

59 of 59 outbound references displayed

  • verified exact3
  • verified fuzzy34
  • unresolved22
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d22457b3-f66b-417f-b8c2-2a4c51f9e0eb · outbound

This paper cites Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.587575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.587575Z digest=sha256:33e410ab42275e3d94f92dc0d0da5c4a9a053bbd334a8ee09b71f56950279f93

Observation 0796061d-d5af-4a3a-b95c-8712d95d73b7 · outbound

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

Effect of Activation Functions on the Training of Overparametrized Neural Nets A convergence theory for deep learning via over-parameterization

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.675536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.592381Z digest=sha256:be19510598264cde293f40fe1d5f16757f2faa9d63200a5f7fb829c14b3353f4

Observation 88ed8d7a-d248-4dce-9390-e52c430045f9 · outbound

This paper cites an unresolved cited work.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-14T13:02:30.664273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.596697Z digest=sha256:59c3dd31ae5acc0f60d0810ee36fe23d569f983f8354914f7c5b898a3ba69473

Observation d01f8fbc-2a64-4645-a6ee-fbb016e62794 · outbound

This paper cites A convergence analysis of gradient descent for deep linear neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets A convergence analysis of gradient descent for deep linear neural networks

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.653151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.601823Z digest=sha256:296f63594975be234e0727695e7e4bc531f3d0962377a36ef968318033bc3a43

Observation bbd2a9cd-2e55-4209-8396-3203f9ba7fc4 · outbound

This paper cites On exact computation with an infinitely wide neural net.

Effect of Activation Functions on the Training of Overparametrized Neural Nets On exact computation with an infinitely wide neural net

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.639962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.606372Z digest=sha256:74826d6503ef3f71f541c8eace15c7e882fa905b664de784795a668b6dd27825

Observation 41d4f581-22a9-4e9a-b9f6-b81f1895f2fd · outbound

This paper cites Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.610258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.610258Z digest=sha256:8df26821133ad82420976d3c0780a4538cbee4c6049026a2b571328b51df0692

Observation a977d621-2fa3-4cd7-86dd-fde7045719aa · outbound

This paper cites Concentration inequalities.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Concentration inequalities

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.614899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.614899Z digest=sha256:90daa4c04587e42079810a42875bab0f5a318e37f0ebace86aa713f58d5f14db

Observation 473c82b4-ef97-4cda-bb08-5aadbffe8d1c · outbound

This paper cites Asymptotic coefficients of hermite function series.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Asymptotic coefficients of hermite function series

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.626440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.618526Z digest=sha256:e8a92d93bc8a7e7bf7f878d6823da29df2dd00744bbc90d292d4d8c11e10af90

Observation 95bb7ea3-0372-4bc8-872c-e42152073108 · outbound

This paper cites SGD learns over-parameterized networks that provably generalize on linearly separable data.

Effect of Activation Functions on the Training of Overparametrized Neural Nets SGD learns over-parameterized networks that provably generalize on linearly separable data

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.614116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.622868Z digest=sha256:e99a076c8020ecd59e37f5a837271a9579012e1050b5ff4f4074f05592e8e993

Observation 8cda9d63-3689-40d3-9463-58843db6b613 · outbound

This paper cites Distributional and L^q norm inequalities for polynomials over convex bodies in R^n.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Distributional and L^q norm inequalities for polynomials over convex bodies in R^n

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.627105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.627105Z digest=sha256:36327f35ef4cf96956b026f258b7a574756699d5a2ee5ed5f9b80cc41ca14008

Observation 6ae86047-14a5-40a2-8647-5a059f21f807 · outbound

This paper cites On the global convergence of gradient descent for over-parameterized models using optimal transport.

Effect of Activation Functions on the Training of Overparametrized Neural Nets On the global convergence of gradient descent for over-parameterized models using optimal transport

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.601119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.631066Z digest=sha256:a7716021d96c118e9f8f184f78679d1b27367c22a0ce13fc137816c51fbde4e9

Observation bf235733-c2c5-468d-831b-50db0b240d97 · outbound

This paper cites Fast and accurate deep network learning by exponential linear units (elus).

Effect of Activation Functions on the Training of Overparametrized Neural Nets Fast and accurate deep network learning by exponential linear units (elus)

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.584173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.634746Z digest=sha256:06a6a67425825aa45b0cb372f7772c18eb7484fe83fc9721e262dca4117ba5de

Observation 62fb232e-5c4b-4c0e-9936-e73091f79a7e · outbound

This paper cites Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.567999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.638094Z digest=sha256:c0c75271ea5e513856ca4ea0face7b6b780d749c26e444e87d06af5371f76693

Observation c32f49e0-59e9-4f6b-b55d-5b1813df0b7d · outbound

This paper cites Du and Jason D.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Du and Jason D

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.550892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.641969Z digest=sha256:af060c18fcb9e42e9c06ad9af7bf2f398148566319605b810e20e0d5d18379b3

Observation 728378ad-362e-40b3-bb80-45d1be067c6f · outbound

This paper cites Du, Xiyu Zhai, Barnabas Poczos, and Aarti Singh.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Du, Xiyu Zhai, Barnabas Poczos, and Aarti Singh

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.537927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.645867Z digest=sha256:e2d3685a89125bb0f6a37fefd8d070b2c943f191afa5f511ae25eb2b2681bda0

Observation e8a1c651-dab7-4dde-8720-bb15a5b31098 · outbound

This paper cites Lee, Haochuan Li, Liwei Wang, and Xiyu Zhai.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Lee, Haochuan Li, Liwei Wang, and Xiyu Zhai

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.525088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.649476Z digest=sha256:015a98a0b0c5a022554ba82274e38696f418acdfdc10c1262a449e5a44719f88

Observation ee15d91c-5640-4181-aab7-69dbbaacacdf · outbound

This paper cites Is it time to swish? comparing deep learning activation functions across nlp tasks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Is it time to swish? comparing deep learning activation functions across nlp tasks

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.510910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.653571Z digest=sha256:b6bd2deaad72ec7e7a85e57de05cb4f2775024d40d84184632311d5592aef476

Observation e7162b87-7cf7-4096-a205-05798684dfba · outbound

This paper cites Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.657503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.657503Z digest=sha256:ad8b0f3089d717e2e979a113c2fdf9d0b35b13f65368b44963e844c69f43ced8

Observation b8bb5666-685f-41fa-b4bd-c47d3d8ff356 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Understanding the difficulty of training deep feedforward neural networks

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.497518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.661789Z digest=sha256:5cbca865f44c6a9e78debf921ae260ef187b95c6eb007ecaf1db23f94a1985db

Observation bc20cae9-8753-4204-9e71-0c855fc02680 · outbound

This paper cites Deep Learning.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Deep Learning

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.665347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.665347Z digest=sha256:51e1651a3fdede89c94f6a3a5f1eb0f34bb52b118af5c27e21578d3198aa50f6

Observation 66ed9f54-a98f-4ac1-abb9-23d5cec584c0 · outbound

This paper cites Which neural net architectures give rise to exploding and vanishing gradients? In S.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Which neural net architectures give rise to exploding and vanishing gradients? In S

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.477693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.669198Z digest=sha256:b7d08c2b0ec291b31464d40733613bd00e6d7a653a122b8ac890979a80f893a3

Observation 58bd3d69-ab74-4cb2-8f20-7cf8a8988a3b · outbound

This paper cites How to start training: The effect of initialization and architecture.

Effect of Activation Functions on the Training of Overparametrized Neural Nets How to start training: The effect of initialization and architecture

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.462505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.673319Z digest=sha256:b764c75732bf3f58115bd88cdc9630b38d7c297a1c2909bde13d269385561b12

Observation 78adc319-e1db-43bd-a83a-28dc61e6cf08 · outbound

This paper cites On the Impact of the Activation Function on Deep Neural Networks Training.

Effect of Activation Functions on the Training of Overparametrized Neural Nets On the Impact of the Activation Function on Deep Neural Networks Training

Reference 23

Resolution
verified exact
local_arxiv, observed 2026-08-14T13:02:30.045025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.676820Z digest=sha256:6d9d446c6ac9dfe8a1533c6bef8ee0244ce20b52a982e7d1820138dd8f978b11

Observation d274fad0-f25c-4e1b-8e7a-9ab01390d29a · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.681234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.681234Z digest=sha256:460b00c097d57ee426247ace511b1e4f37293e43cbdc8ad543d8d7bd5f61c5eb

Observation 1b197844-f1b4-41ad-8cf7-8cc7032b4c78 · outbound

This paper cites Contributions to the theory of H ermitian series.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Contributions to the theory of H ermitian series

Reference 25

Resolution
verified exact
doi, observed 2026-08-14T13:02:29.913221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.685205Z digest=sha256:ff39eb5c5df38021926e508544aaa56135470884014d100f4f489ea992ab9f5b

Observation faa498f1-1221-4fdc-b35d-736af877ffd2 · outbound

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

Effect of Activation Functions on the Training of Overparametrized Neural Nets Neural tangent kernel: Convergence and generalization in neural networks

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.440746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.689628Z digest=sha256:32d1300de922425f4980b540cfe9dffe914431912d7e17dc53725332982519a7

Observation c1b5bad9-eb0e-4505-95c5-f0404cac7421 · outbound

This paper cites Solutions to some functional equations and their applications to characterization of probability distributions.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Solutions to some functional equations and their applications to characterization of probability distributions

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.426465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.693842Z digest=sha256:3fa1af7d778a3aa76b5ede81595b2e872240f78d3fc802c90e4577c75e158934

Observation fc10c694-2cfe-49f2-986a-c9807586c754 · outbound

This paper cites On the expressive power of deep polynomial neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets On the expressive power of deep polynomial neural networks

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.410998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.697932Z digest=sha256:67ff973342c815d76d45df7dc2e678120e41445069bb6af7fbdbf35dbfa60549

Observation ef3e5435-e305-4795-89a6-e00f2d09ef6f · outbound

This paper cites Self-normalizing neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Self-normalizing neural networks

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.396988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.701260Z digest=sha256:635029575c00987ca7841d2e30e6389a211841a3aa8529e72009fc0dd0486230

Observation f0032b5c-8fe3-4989-a7b4-ed6d4306d0ec · outbound

This paper cites Learning multiple layers of features from tiny images.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Learning multiple layers of features from tiny images

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.704274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.704274Z digest=sha256:3a9ca2210a99b100d0706e0f86e58ec82ff9e962db961afc182826ab55e9de5c

Observation 58edd59d-c58a-4513-942a-5e39545a4906 · outbound

This paper cites Adaptive estimation of a quadratic functional by model selection.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Adaptive estimation of a quadratic functional by model selection

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.376053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.707973Z digest=sha256:4af5222e307ab149b15d995ce2866610d56c13e4ecacbba0e5af63c4c44bae0a

Observation fea9840c-3e3a-4905-afcd-afc006ccb2ac · outbound

This paper cites an unresolved cited work.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Unresolved cited work

Reference 32

Resolution
unresolved
raw_fallback, observed 2026-08-14T13:02:30.361067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.711672Z digest=sha256:15806ae8bdf43c228961f8f4abf7478e2bfa30217815b988370c35675f44e5d2

Observation ad4a556b-ed4f-487a-93d7-660fbd6f433c · outbound

This paper cites Deep Neural Networks as Gaussian Processes.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Deep Neural Networks as Gaussian Processes

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.715502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.715502Z digest=sha256:1a595931832423960c8314374db37679347365eea7b3447ea1f8b0859af232b2

Observation c6f82c84-3aa6-4172-8069-409597f63f1f · outbound

This paper cites Lin, Allan Pinkus, and Shimon Schocken.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Lin, Allan Pinkus, and Shimon Schocken

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.719277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.719277Z digest=sha256:afdea0256d0c835eb62db8c477b89c9bdbf4035244fb6d34c6a61cd74e3123bd

Observation 702eaa01-e401-4819-b2ef-17a73968f821 · outbound

This paper cites Learning overparameterized neural networks via stochastic gradient descent on structured data.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Learning overparameterized neural networks via stochastic gradient descent on structured data

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.348543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.723440Z digest=sha256:c6ecbaabecc349513c70ab7cd51e75a021f8fc02b647e665911679a418ec355f

Observation ea169329-dce7-4292-8b7e-0acd9018ec7f · outbound

This paper cites A random matrix approach to neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets A random matrix approach to neural networks

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.729066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.729066Z digest=sha256:9090b10f563397c7444d0917e1f39114518e3e4394dba0af42b440d8dcc2526c

Observation c5b7705d-df9d-4c24-94a3-ed122f055a10 · outbound

This paper cites Mason and D.C.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Mason and D.C

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.336215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.732757Z digest=sha256:44d39fb330c80656b533fd018c1a8fa6f8433c4f5dd3ee548e163aea06285796

Observation b65ce0b7-cf44-45b1-a65e-33ee087de431 · outbound

This paper cites A mean field view of the landscape of two-layer neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets A mean field view of the landscape of two-layer neural networks

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.736156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.736156Z digest=sha256:12b5b2bd46956d258597b49f104ff933f6290aa741a2d88b0e6515e98637ee96

Observation 9d82245d-47ec-4307-b77f-c0f7c09961f8 · outbound

This paper cites In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning.

Effect of Activation Functions on the Training of Overparametrized Neural Nets In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.740335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.740335Z digest=sha256:bf0f8329c7e5d67246f90382c90c446d654ab1752a42fe3ca8f71f620b0e5102

Observation 14db2195-9b00-4e59-9094-354ddea74804 · outbound

This paper cites Activation Functions: Comparison of trends in Practice and Research for Deep Learning.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Activation Functions: Comparison of trends in Practice and Research for Deep Learning

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.744348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.744348Z digest=sha256:33a809b4a8c14340dcf2c22c52dc111ae0669d8f0f7552e4918d1c21838fe0ce

Observation 092848dc-6bf1-4c10-af24-dabba027adb5 · outbound

This paper cites Analysis of boolean functions.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Analysis of boolean functions

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.322826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.749719Z digest=sha256:6a3201c38d949b33968e6fb780bc9e7a027bd0666cc41e00ea37cfaa8f33cc1c

Observation e26f7eb3-2f22-4f8e-8a25-243e52c7ee4b · outbound

This paper cites Towards moderate overparameterization: global convergence guarantees for training shallow neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Towards moderate overparameterization: global convergence guarantees for training shallow neural networks

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.753639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.753639Z digest=sha256:edafb3b1431b278e1a808c66527051f8478f8bb772ea136fd7df4772a85d94b4

Observation 2448825e-dfc5-41e5-953f-6a2f54af1979 · outbound

This paper cites Nonlinear random matrix theory for deep learning.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Nonlinear random matrix theory for deep learning

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.311595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.757937Z digest=sha256:e4235f7286f552d29f0a8b583af7fd684e0ac0660fa938644993d9e4a919db4c

Observation 043f1295-2966-4952-a5d0-453f68b089ce · outbound

This paper cites The spectrum of the fisher information matrix of a single-hidden-layer neural network.

Effect of Activation Functions on the Training of Overparametrized Neural Nets The spectrum of the fisher information matrix of a single-hidden-layer neural network

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.300185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.761350Z digest=sha256:a0f3b05d67d33077d558f6cabfbc250f81df1a79df9090ccaed38d06cfaf457d

Observation 6e5a7a6c-6e89-46f2-91ff-ad4d46bb6d8d · outbound

This paper cites Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.285600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.764677Z digest=sha256:12034716eec02811dc8a47ee20beef622e008b7fca4eb2d5d5dfc6996bdd36ab

Observation 9419fa2b-9418-4b64-96b4-24e0d17f8e89 · outbound

This paper cites Schoenholz, and Surya Ganguli.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Schoenholz, and Surya Ganguli

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.272768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.767571Z digest=sha256:90a5a74deaee6d0abf971424bf3eafbacff0e1b71d38cce8492c2691978b67df

Observation 85fd894e-e22e-4605-bae1-8e37706345d3 · outbound

This paper cites Approximation theory of the MLP model in neural networks.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Approximation theory of the MLP model in neural networks

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.770992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.770992Z digest=sha256:e577c2887d81062cbde0592ad4e84e3d7190b9dd2b600f5e278e2bac32fd3087

Observation ab726565-5313-4c22-80fc-5bef765f4063 · outbound

This paper cites an unresolved cited work.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-14T13:02:30.260402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.775006Z digest=sha256:5e87ab240f52a2c6bb26cd65f9aa380c848e1a473fcf08887b2553888a304e8e

Observation 62839b48-f4ac-4c86-bdf8-e41807a845ed · outbound

This paper cites Smallest singular value of a random rectangular matrix.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Smallest singular value of a random rectangular matrix

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.247270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.778894Z digest=sha256:53a76da9391ac3a2bf616d7df7aab19bb64aadd467cb2b27e8305e207bdf4c7a

Observation 1f5371f0-0ba6-4aeb-ae0a-3ac7a7fe71d0 · outbound

This paper cites Learning kernel-based halfspaces with the 0-1 loss.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Learning kernel-based halfspaces with the 0-1 loss

Reference 50

Resolution
verified exact
doi, observed 2026-08-14T13:02:29.866153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.782746Z digest=sha256:56452d498c2053437ec06969b2248f17e524596d4e37ea46305744b45ac24eb7

Observation ff541934-d291-4a0b-b203-90ed3e2bc450 · outbound

This paper cites Neural network with unbounded activation functions is universal approximator.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Neural network with unbounded activation functions is universal approximator

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.786749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.786749Z digest=sha256:976f33db7c91ec02e1b3d52c8ab3a252a087924462888231b0442bb3831377d0

Observation 2fb2c7c4-6d91-443a-8318-e9a3f82de050 · outbound

This paper cites Spielman and Shang - Hua Teng.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Spielman and Shang - Hua Teng

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.790832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.790832Z digest=sha256:62cdf7fdc110c6bd6189e0eebec8915007dfb901f00b75a3dccc732cbd7f0af6

Observation a34dbaa2-04af-403e-bb4d-7e4563245464 · outbound

This paper cites Orthogonal polynomials.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Orthogonal polynomials

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.234136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.793919Z digest=sha256:517f727241121b3708e5496af24d569b68d257d6464034baafcbd27195816eef

Observation 4fd9fd0f-a19b-4adc-b86d-eb41fe55d2f5 · outbound

This paper cites Lectures on H ermite and L aguerre expansions , volume 42 of Mathematical Notes.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Lectures on H ermite and L aguerre expansions , volume 42 of Mathematical Notes

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.220882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.796835Z digest=sha256:8491e3ed9233ea94dd91114a83c00f66063889fe2289691779f6c39cbfe6a9c6

Observation 37d0ad4b-dd6c-4ff1-84f4-925e987faada · outbound

This paper cites Invariance of weight distributions in rectified mlps.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Invariance of weight distributions in rectified mlps

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.208666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.799938Z digest=sha256:63b3d26b6e55ccb9fed7ce5ec360c9ab570e1aad55db4ea9dbd98ae6d3de46bd

Observation 1ad9c1a3-2098-49b3-9278-8d33845db6d9 · outbound

This paper cites Ger s gorin and his circles , volume 36.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Ger s gorin and his circles , volume 36

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.197116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.803233Z digest=sha256:75e2a3950dd536e5782b157f0de6e11e3af6a766ad6a403b3e64b5ea1e65b94f

Observation 75988217-aebb-44a7-9e99-78be683f461c · outbound

This paper cites Das asymptotische V erteilungsgesetz der E igenwerte linearer partieller D ifferentialgleichungen (mit einer A nwendung auf die T heorie der H ohlraumstrahlung).

Effect of Activation Functions on the Training of Overparametrized Neural Nets Das asymptotische V erteilungsgesetz der E igenwerte linearer partieller D ifferentialgleichungen (mit einer A nwendung auf die T heorie der H ohlraumstrahlung)

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-14T13:02:29.806990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T13:02:29.806990Z digest=sha256:fcf8b057e3e275b4c308f2c72f00d117e8a68e718df1923139ad8f1094dd71c2

Observation 461b217f-a1a3-4c04-87cc-c61dd1fc5b81 · outbound

This paper cites Diverse neural network learns true target functions.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Diverse neural network learns true target functions

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.183720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.811341Z digest=sha256:c8360b0fa89a0279dfed3ec85a752262147f50bbba7174b9947de86aa0e1d672

Observation 9211ccd6-05ec-414f-9838-f3c65a5f081c · outbound

This paper cites Revise saturated activation functions.

Effect of Activation Functions on the Training of Overparametrized Neural Nets Revise saturated activation functions

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T13:02:30.170883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-08-14T13:02:29.815116Z digest=sha256:b648422b4f7d12bb5b541899c2af1ae07de66f2eda6ee9635d91f1cdc1227d71

Pith citing papers

No inbound Pith citation observations are available.