Paper Citation Record · LEDGER

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks

As of 10 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2509.00362.

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

pith.paper-citation-record.v1
2509.00362 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:54:42.655542Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

46 of 46 outbound references displayed

verified exact0
verified fuzzy31
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e4aa0bc7-9e5a-44d7-9138-4ab5b4f3b988 · outbound

This paper cites The Principles of Deep Learning Theory.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks The Principles of Deep Learning Theory

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:38.337984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb3e46d1-ddea-4f89-9962-93a51c5bdf49 · outbound

This paper cites Goodfellow, Y.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Goodfellow, Y

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:49.641890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 545a1f57-a38d-41a6-b8d0-96025c70060f · outbound

This paper cites Learning deep architectures for ai,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Learning deep architectures for ai,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:49.426227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16eb901e-4d48-473d-8263-e25e8ad01293 · outbound

This paper cites Deep learning,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Deep learning,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:38.585150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8556232-9b0e-4d06-80ad-567df169b552 · outbound

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

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Understanding the difficulty of training deep feedforward neural networks,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:38.661587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db7f36d-6171-40f3-b94b-70dec21a8216 · outbound

This paper cites Rectified linear units improve restricted boltzmann machines,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Rectified linear units improve restricted boltzmann machines,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:49.217684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 96b7fce7-9f10-4413-81d7-84976f8f4933 · outbound

This paper cites Rectifier nonlinearities improve neural network acoustic models,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Rectifier nonlinearities improve neural network acoustic models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:49.017961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0f294dad-f83a-437c-b11b-1adace5a5f99 · outbound

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

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:39.009593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c00c4bd-60ce-459d-b28d-b17ffef4afea · outbound

This paper cites Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs).

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:39.091827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37c2f40e-c271-4a72-ad5a-c3bd5279d82d · outbound

This paper cites Deep residual learning for image recognition,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Deep residual learning for image recognition,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:39.196225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a749d5d2-567e-4753-a16c-7454e20071af · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Batch normalization: Accelerating deep network training by reducing internal covariate shift,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:48.831261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e7664735-e697-4e83-b4d2-36e3bfc4b706 · outbound

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

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:48.602039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e7de407-4a55-4d88-8128-f98ce33ada94 · outbound

This paper cites Exact solutions to the nonlinear dynamics of learning in deep linear neural networks.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:39.504363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8df18806-8dee-476a-9ef4-37536b392467 · outbound

This paper cites Improved weight initialization for deep and narrow feedforward neural network,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Improved weight initialization for deep and narrow feedforward neural network,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:48.391769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9852b251-9cd6-4f0e-b23e-fd64527a498a · outbound

This paper cites Gradient-based learning applied to document recognition,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Gradient-based learning applied to document recognition,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:39.698745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bbafe7b-d449-4fe0-9bd1-b669fd9c39f4 · outbound

This paper cites Greedy layer-wise training of deep networks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Greedy layer-wise training of deep networks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:48.159720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b29e9942-9c55-4277-9433-e902fc8a8590 · outbound

This paper cites Learning repre- sentations by back-propagating errors,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Learning repre- sentations by back-propagating errors,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:47.969909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 47b2b7fb-4ce4-4127-8047-007a5efe0f00 · outbound

This paper cites Backpropagation applied to handwritten zip code recognition,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Backpropagation applied to handwritten zip code recognition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:47.753489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation df1e04ef-e002-4421-b7b4-dc71ddd32eed · outbound

This paper cites Dying ReLU and Initialization: Theory and Numerical Examples.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Dying ReLU and Initialization: Theory and Numerical Examples

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:40.117887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb25dd60-b402-40b0-9342-c3bd2767945f · outbound

This paper cites Robust weight initialization for tanh neural networks with fixed point analysis,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Robust weight initialization for tanh neural networks with fixed point analysis,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:47.505430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 992c3cc1-1e2b-42b5-bdb6-65452b67badb · outbound

This paper cites Revisiting weight initialization of deep neural networks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Revisiting weight initialization of deep neural networks,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:47.253192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 49db1ae4-ae3d-43b0-89d1-d8fcabd6e020 · outbound

This paper cites Provable benefit of orthogonal initialization in optimizing deep linearnetworks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Provable benefit of orthogonal initialization in optimizing deep linearnetworks,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:46.926542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 68f188dd-950c-4bd2-8db3-36e116f81b6a · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:40.453364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0a7a0b3-39f4-4558-9391-5cdde1e52974 · outbound

This paper cites Computational optimal transport: With applications to data science,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Computational optimal transport: With applications to data science,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:46.681510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 50e763ff-8fe3-409a-92da-b9981251a4de · outbound

This paper cites an unresolved cited work.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:40.640379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c62ef329-0ff5-43a1-aff2-fc0471f683c9 · outbound

This paper cites How to generate random matrices from the classical compact groups.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks How to generate random matrices from the classical compact groups

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:40.704791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3340867c-22c0-46f0-8f1a-86f103cf3e93 · outbound

This paper cites an unresolved cited work.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:54:46.362403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 63fdffbe-224f-444b-8031-9f209299d1e6 · outbound

This paper cites Mean field residual networks: On the edge of chaos,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Mean field residual networks: On the edge of chaos,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:46.065471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f07fb28b-ef17-4a94-b81b-c6be7d2c9732 · outbound

This paper cites Skewness and kurtosis in real data samples,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Skewness and kurtosis in real data samples,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:45.831819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5be93ecb-e2e5-4784-a979-cfb714cabfb8 · outbound

This paper cites Transforming variables to central normality,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Transforming variables to central normality,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:45.585323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a9ce912d-6ebd-4f40-b737-63349f450ebb · outbound

This paper cites A comparison principle for functions of a uniformly random subspace,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks A comparison principle for functions of a uniformly random subspace,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:45.417588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2cc4855d-b4ac-497a-b5d4-03e4c6d9b4c2 · outbound

This paper cites Maxima of entries of haar distributed matrices,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Maxima of entries of haar distributed matrices,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:45.266258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b748df7b-a0bb-4c10-a1fd-4537dc5f68a4 · outbound

This paper cites A multivariate berry–esseen theorem with explicit constants,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks A multivariate berry–esseen theorem with explicit constants,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:45.125585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 22ea0ccd-1623-411c-aa17-71f71db790c6 · outbound

This paper cites an unresolved cited work.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:54:44.954032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b09b980d-6478-4ff2-b8c9-3f232b86d2ac · outbound

This paper cites Deep Information Propagation.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Deep Information Propagation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:41.698132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d73c2608-812b-4481-a942-17f09ada5173 · outbound

This paper cites On numerical computation for the distribution of the convolution of N independent rectified Gaussian variables,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks On numerical computation for the distribution of the convolution of N independent rectified Gaussian variables,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:44.809342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 89cc8e28-2522-4a55-be14-290b9ce4385f · outbound

This paper cites An analytic solution to covariance propagation in neural networks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks An analytic solution to covariance propagation in neural networks,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:44.638529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f4f919c9-1bd7-4544-8042-9b6d310462b5 · outbound

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

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks How to start training: The effect of initialization and architecture,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:44.478154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5dc06971-54f9-4f6b-aae9-77d7cf93878f · outbound

This paper cites Tensor programs VI: Feature learning in infinite depth neural networks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Tensor programs VI: Feature learning in infinite depth neural networks,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:44.300378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ea2258ea-e22e-46d4-9b71-3840855cdd06 · outbound

This paper cites Self- normalizing neural networks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Self- normalizing neural networks,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:44.090831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e792a62-88eb-4830-8cc7-83f53491ac56 · outbound

This paper cites Becker and R.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Becker and R

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:43.925886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7801ff5b-3f05-4d26-8995-d3cf7e2a814c · outbound

This paper cites Breast cancer wisconsin (diagnostic),.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Breast cancer wisconsin (diagnostic),

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:43.777193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1e07b7b6-48be-4400-970d-ab7e79800402 · outbound

This paper cites Using the adap learning algorithm to forecast the onset of diabetes mellitus,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Using the adap learning algorithm to forecast the onset of diabetes mellitus,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:43.634921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e0bb75e-e000-4dec-a12d-ec29eaac6aae · outbound

This paper cites Classification of radar returns from the ionosphere using neural networks,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Classification of radar returns from the ionosphere using neural networks,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:43.485816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a7a056a5-157b-4ce6-b695-bfc30dad2f4d · outbound

This paper cites Aeberhard and M.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Aeberhard and M

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:43.297316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f78070c5-967c-4984-9d5e-a22021ad85dc · outbound

This paper cites Least angle regression,.

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Least angle regression,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:54:43.135410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

No inbound Pith citation observations are available.