Paper Citation Record · LEDGER

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization

As of 18 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 1 inbound Pith citation observation for arXiv:2412.02153.

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

pith.paper-citation-record.v1
2412.02153 v2

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T23:55:18.298267Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-07T10:57:04.360455Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T09:26:25.980990Z

Reference resolution

52 of 52 outbound references displayed

verified exact0
verified fuzzy30
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d27cd9ed-7dde-4c26-8e3d-246a2fdad191 · outbound

This paper cites SIAM review, 60(2):223–311, 2018.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization SIAM review, 60(2):223–311, 2018

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.875502Z

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 fbc0659b-0346-4dc8-bac3-3b6acd5abaa7 · outbound

This paper cites Adaptivesubgradientmethodsforonlinelearning and stochastic optimization.Journal of machine learning research, 12(7), 2011.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Adaptivesubgradientmethodsforonlinelearning and stochastic optimization.Journal of machine learning research, 12(7), 2011

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.863774Z

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 0b55d37c-ec4e-489f-a94f-f40e7caf39ea · outbound

This paper cites Neuralnetworksformachinelearning lecture 6a overview of mini-batch gradient descent.Cited on, 14(8):2, 2012.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Neuralnetworksformachinelearning lecture 6a overview of mini-batch gradient descent.Cited on, 14(8):2, 2012

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.851195Z

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 7154ba05-afe1-4f39-92c0-adf66094f4ee · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Adam: A Method for Stochastic Optimization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.102499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791857b2-973e-4f78-a31b-d11c903f21e4 · outbound

This paper cites Why adam outperforms gradient descent on language models: A heavy-tailed class imbalance problem.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Why adam outperforms gradient descent on language models: A heavy-tailed class imbalance problem

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.839261Z

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 5d3d1554-d265-4b76-8d1e-8be221b1f8a0 · outbound

This paper cites Toward Understanding Why Adam Converges Faster Than SGD for Transformers.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Toward Understanding Why Adam Converges Faster Than SGD for Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.115103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74ba7857-1527-425f-ab0b-7398f40742e2 · outbound

This paper cites an unresolved cited work.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-11T23:55:18.826280Z

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 c5191b5a-a2da-49eb-80b0-249757cd9174 · outbound

This paper cites Why Transformers Need Adam: A Hessian Perspective.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Why Transformers Need Adam: A Hessian Perspective

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.123604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d40876-d56f-4502-a5ef-fc0265e9f73d · outbound

This paper cites Adam can converge without any modification on update rules.Advances in neural information processing systems, 35:28386–28399, 2022.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Adam can converge without any modification on update rules.Advances in neural information processing systems, 35:28386–28399, 2022

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.815678Z

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 0e254062-20e2-40e9-8364-d3a6bf27174b · outbound

This paper cites Ontheconvergenceofadamandbeyond.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Ontheconvergenceofadamandbeyond

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.804212Z

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 b531cc5b-adf0-4d4e-9c55-05dde3af477c · outbound

This paper cites Onthevarianceoftheadaptivelearningrateandbeyond.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Onthevarianceoftheadaptivelearningrateandbeyond

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.793186Z

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 eeb74156-0b34-4583-9847-c698e58a1d5a · outbound

This paper cites Adaptive gradient methods with dy- namic bound of learning rate.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Adaptive gradient methods with dy- namic bound of learning rate

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.781935Z

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 2a2d0d84-fbfa-4931-a3ae-5280e971826b · outbound

This paper cites Adabelief optimizer: Adapting stepsizes by the belief in observed gradients.Advances in neural information processing systems, 33:18795–18806, 2020.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Adabelief optimizer: Adapting stepsizes by the belief in observed gradients.Advances in neural information processing systems, 33:18795–18806, 2020

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.143664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60c21456-6732-4846-908e-81c9634db9b2 · outbound

This paper cites Momentum is all you need for data-driven adaptive optimization.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Momentum is all you need for data-driven adaptive optimization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.762047Z

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 fd2b5e40-05e0-4b00-bfc2-808a81e52afa · outbound

This paper cites Survey of optimization algo- rithms in modern neural networks.Mathematics, 11(11):2466, 2023.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Survey of optimization algo- rithms in modern neural networks.Mathematics, 11(11):2466, 2023

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.749731Z

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 4e825763-1ff0-458c-bf6f-5ebb7ecc4d23 · outbound

This paper cites No train no gain: Revisitingefficienttrainingalgorithmsfortransformer-basedlanguagemodels.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization No train no gain: Revisitingefficienttrainingalgorithmsfortransformer-basedlanguagemodels

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.733754Z

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 9503e7e6-637f-4e50-8912-3ff3dea5a0b7 · outbound

This paper cites Attention is all you need.Advances in Neural Information Processing Systems, 2017.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Attention is all you need.Advances in Neural Information Processing Systems, 2017

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.159144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 616b0594-0698-463c-b76b-efe36d10d86f · outbound

This paper cites Dissecting adam: The sign, magnitude and variance of stochastic gradients.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Dissecting adam: The sign, magnitude and variance of stochastic gradients

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.714484Z

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 e3e569c9-d134-4e9a-91e2-950098a2c5d8 · outbound

This paper cites Noise is not the main factor behind the gap between sgd and adam on transformers, but sign descent might be.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Noise is not the main factor behind the gap between sgd and adam on transformers, but sign descent might be

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.700866Z

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 483bd74d-39e7-4e6f-ab3b-bc86c1cfd077 · outbound

This paper cites Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.171126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fedc59b5-eaae-43be-8a59-e702ccc86ad0 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.174774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c18c163d-93a1-47ce-b256-7de82ad31881 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization An image is worth 16x16 words: Transformers for image recognition at scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.178936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bee428aa-ab62-43fa-afe1-524ba5a3c689 · outbound

This paper cites Escaping the Big Data Paradigm with Compact Transformers.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Escaping the Big Data Paradigm with Compact Transformers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.183017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee7bd2b8-1511-4123-9a25-16db88075725 · outbound

This paper cites Improving transformer op- timization through better initialization.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Improving transformer op- timization through better initialization

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.681565Z

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 d2bc7fba-6729-4177-b206-a07a6563fe18 · outbound

This paper cites Scan and snap: Understanding trainingdynamicsandtokencompositionin1-layertransformer.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Scan and snap: Understanding trainingdynamicsandtokencompositionin1-layertransformer

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.669067Z

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 3dea8294-5312-4dad-8477-2a38c972e11a · outbound

This paper cites On the difficulty of training Recurrent Neural Networks.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization On the difficulty of training Recurrent Neural Networks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.194230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1632498-320c-4c21-ac5a-f62c91ea4c9d · outbound

This paper cites Visualizing the loss landscape of neural nets.Advances in neural information processing systems, 31, 2018.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Visualizing the loss landscape of neural nets.Advances in neural information processing systems, 31, 2018

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.198263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9e78a07-1177-471e-9b03-3a0ee96d91df · outbound

This paper cites On the sdes and scal- ing rules for adaptive gradient algorithms.Advances in Neural Information Processing Systems, 35:7697–7711, 2022.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization On the sdes and scal- ing rules for adaptive gradient algorithms.Advances in Neural Information Processing Systems, 35:7697–7711, 2022

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.650192Z

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 e2030e20-49c8-4dec-9706-1db481a493ab · outbound

This paper cites an unresolved cited work.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-11T23:55:18.638428Z

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 b306e551-bd51-4afc-b145-a2dc601c30f5 · outbound

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

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Understanding the difficulty of training deep feedforward neural networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.214398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa438afe-3957-41d3-a43e-215acaba8e28 · outbound

This paper cites On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.218036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3239ca3-1b01-4c0f-bc14-0c8ed465182f · outbound

This paper cites Deep residual learning for image recognition.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Deep residual learning for image recognition

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.620554Z

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 6e4a4f91-c95a-47b0-8350-dd3f958c4894 · outbound

This paper cites Generative adversarial networks.Communications of the ACM, 63(11):139–144, 2020.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Generative adversarial networks.Communications of the ACM, 63(11):139–144, 2020

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.609138Z

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 aa2311f3-a0de-4ec4-9659-49bacba4de32 · outbound

This paper cites Long short-term memory.Neural Computation, 9(8):1735–1780, 1997.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Long short-term memory.Neural Computation, 9(8):1735–1780, 1997

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.597359Z

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 9ec2b5c5-28f0-4b26-8b76-093774850168 · outbound

This paper cites A stochastic approximation method.The annals of mathe- matical statistics, pages 400–407, 1951.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization A stochastic approximation method.The annals of mathe- matical statistics, pages 400–407, 1951

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.585088Z

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 f29ab8a6-0f0f-4bc1-b165-631fff1c70a3 · outbound

This paper cites Some methods of speeding up the convergence of iteration methods.Ussr computational mathematics and mathematical physics, 4(5):1–17, 1964.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Some methods of speeding up the convergence of iteration methods.Ussr computational mathematics and mathematical physics, 4(5):1–17, 1964

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.239074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae64e145-0cc5-4fda-b4f1-9bc6ba3983c6 · outbound

This paper cites Decoupled weight decay regularization.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Decoupled weight decay regularization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.243371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b053159-668b-4b04-baf2-91b25ac8acf6 · outbound

This paper cites Learningmultiplelayersoffeaturesfromtinyimages.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Learningmultiplelayersoffeaturesfromtinyimages

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.557433Z

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 767f1587-9603-4c95-a5d5-ead3f3c3b69e · outbound

This paper cites Imagenet large scale visual recognition challenge.International journal of computer vision, 115:211–252, 2015.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Imagenet large scale visual recognition challenge.International journal of computer vision, 115:211–252, 2015

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.250663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8485ca84-2abe-4b3b-848f-a44ac385636e · outbound

This paper cites Building a large annotated corpus of english: The penn treebank.Computational linguistics, 19(2):313–330, 1993.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Building a large annotated corpus of english: The penn treebank.Computational linguistics, 19(2):313–330, 1993

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.254472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 623c7226-ab06-4426-9dfe-b0543400e1c1 · outbound

This paper cites fairseq: A fast, extensible toolkit for sequence modeling.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization fairseq: A fast, extensible toolkit for sequence modeling

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.533290Z

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 fe6288ff-e5e5-494e-b28a-d770ca723e25 · outbound

This paper cites Bleu: amethodforautomatic evaluation of machine translation.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Bleu: amethodforautomatic evaluation of machine translation

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.521952Z

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 b8bfc735-fe4c-4d20-b7fd-e98bc15aedaf · outbound

This paper cites Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.265028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae5cb523-8896-457c-bfa7-14d0dbffc699 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.Ad- vances in neural information processing systems, 30, 2017.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Gans trained by a two time-scale update rule converge to a local nash equilibrium.Ad- vances in neural information processing systems, 30, 2017

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.510175Z

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 3873b934-4b51-4775-aa0d-001588530268 · outbound

This paper cites Asymmetric valleys: Beyond sharp and flat local minima.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Asymmetric valleys: Beyond sharp and flat local minima

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.499600Z

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 36084f00-71b3-4382-ba2a-97d75361106a · outbound

This paper cites Towards the- oretically understanding why sgd generalizes better than adam in deep learning.Advances in Neural Information Processing Systems, 33:21285–21296, 2020.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Towards the- oretically understanding why sgd generalizes better than adam in deep learning.Advances in Neural Information Processing Systems, 33:21285–21296, 2020

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.487962Z

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 9b683fd7-1aef-43d0-bb67-1032c1c28dfc · outbound

This paper cites On the adequacy of untuned warmup for adaptive optimization.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization On the adequacy of untuned warmup for adaptive optimization

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.475374Z

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 4de66683-7cb4-4aa8-948d-f2f6eb1234f1 · outbound

This paper cites Re- thinkingtheinceptionarchitectureforcomputervision.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Re- thinkingtheinceptionarchitectureforcomputervision

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.464169Z

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 7b7fe0e2-1d91-49d4-9b38-9a320a418488 · outbound

This paper cites SGDR: Stochastic gradient descent with warm restarts.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization SGDR: Stochastic gradient descent with warm restarts

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T23:55:18.287122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 018f5842-299b-4eae-9179-df7b4a65e0df · outbound

This paper cites Linear mode connectivity and the lottery ticket hypothesis.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization Linear mode connectivity and the lottery ticket hypothesis

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.445825Z

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 478ed16b-4bee-4527-bf8a-ceb2170032bf · outbound

This paper cites The small denominator leads to excessively large initial updates, particularly when¯g is small orσ2 is large.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization The small denominator leads to excessively large initial updates, particularly when¯g is small orσ2 is large

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:55:18.434649Z

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 9c013d2f-01a8-4f6a-98c3-74560a32b667 · outbound

This paper cites The model is trained with a length penalty of 1.0, a beam size of 5, and an initial warmup step size of10−7.

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization The model is trained with a length penalty of 1.0, a beam size of 5, and an initial warmup step size of10−7

Reference 52

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T23:55:18.423003Z

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.

Pith citing papers

Observation c147f485-ea7b-4125-8d91-2a028299233c · inbound

A Provably Robust Multi-Jet Framework applied to Active Flow Control of an Airfoil in Weakly Compressible Flow cites this paper.

A Provably Robust Multi-Jet Framework applied to Active Flow Control of an Airfoil in Weakly Compressible Flow Revisiting the Initial Steps in Adaptive Gradient Descent Optimization

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:26:25.982708Z

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.