Spectral-factorized Positive-definite Curvature Learning for NN Training | Paper Citation Record

Observation d516fe53-433f-42f1-9386-2e893b3b7b03 · outbound

This paper cites write newline.

Spectral-factorized Positive-definite Curvature Learning for NN Training write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.093925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37413ba1-3c82-4b0d-a097-391378fb0cd4 · outbound

This paper cites Optimization algorithms on matrix manifolds.

Spectral-factorized Positive-definite Curvature Learning for NN Training Optimization algorithms on matrix manifolds

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.417655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c4db66ff-bcb0-46a3-936f-d056de873a1b · outbound

This paper cites Efficient full-matrix adaptive regularization.

Spectral-factorized Positive-definite Curvature Learning for NN Training Efficient full-matrix adaptive regularization

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.404868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ca5bc144-a454-47bc-97b4-0d2edeba16e8 · outbound

This paper cites Learning rate grafting: Transferability of optimizer tuning.

Spectral-factorized Positive-definite Curvature Learning for NN Training Learning rate grafting: Transferability of optimizer tuning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.391647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d84ea81d-27e2-4982-9214-dcaf111bb66d · outbound

This paper cites Natural gradient works efficiently in learning.

Spectral-factorized Positive-definite Curvature Learning for NN Training Natural gradient works efficiently in learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.113641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea743440-49b2-421d-9cce-490e99bad129 · outbound

This paper cites Information geometry and its applications, volume 194.

Spectral-factorized Positive-definite Curvature Learning for NN Training Information geometry and its applications, volume 194

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.368155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 00e2c0a0-7921-4570-9563-a03e45f402ca · outbound

This paper cites Scalable Second Order Optimization for Deep Learning.

Spectral-factorized Positive-definite Curvature Learning for NN Training Scalable Second Order Optimization for Deep Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.123382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c04a15-7dc6-4cc4-a748-cab14c7c14b2 · outbound

This paper cites Old Optimizer, New Norm: An Anthology.

Spectral-factorized Positive-definite Curvature Learning for NN Training Old Optimizer, New Norm: An Anthology

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.128452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c6fa4ac-c613-48d0-b3c6-cad7b79de2a0 · outbound

This paper cites Better plain ViT baselines for ImageNet-1k.

Spectral-factorized Positive-definite Curvature Learning for NN Training Better plain ViT baselines for ImageNet-1k

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.133167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c41f817e-9a1c-4a8a-a5dd-24d5a9608ed2 · outbound

This paper cites Manopt, a matlab toolbox for optimization on manifolds.

Spectral-factorized Positive-definite Curvature Learning for NN Training Manopt, a matlab toolbox for optimization on manifolds

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.354545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 49abba08-f9fe-463c-8d02-ae60413aecd2 · outbound

This paper cites S., Sra, S., and Tropp, J.

Spectral-factorized Positive-definite Curvature Learning for NN Training S., Sra, S., and Tropp, J

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.341312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bfb5ef71-6a46-4399-9b00-2dec1431e214 · outbound

This paper cites Closing the generalization gap of adaptive gradient methods in training deep neural networks.

Spectral-factorized Positive-definite Curvature Learning for NN Training Closing the generalization gap of adaptive gradient methods in training deep neural networks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.328043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7615c643-16ed-474f-ad7f-04698c8c0a9e · outbound

This paper cites Symbolic Discovery of Optimization Algorithms.

Spectral-factorized Positive-definite Curvature Learning for NN Training Symbolic Discovery of Optimization Algorithms

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.150424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0e3e54d-d70d-4a47-999c-20c17f630a06 · outbound

This paper cites Z., Huang, J., Reich, S., and Stuart, A.

Spectral-factorized Positive-definite Curvature Learning for NN Training Z., Huang, J., Reich, S., and Stuart, A

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.313727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 262b1a58-0d27-4111-bb45-9f3713acef7d · outbound

This paper cites On Empirical Comparisons of Optimizers for Deep Learning.

Spectral-factorized Positive-definite Curvature Learning for NN Training On Empirical Comparisons of Optimizers for Deep Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.158626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44f0adb-6656-4b28-a66d-59000abda482 · outbound

This paper cites and Mehta, H.

Spectral-factorized Positive-definite Curvature Learning for NN Training and Mehta, H

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.164008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94d03f1e-902c-4587-b65c-e32c24bc1a72 · outbound

This paper cites Adaptive subgradient methods for online learning and stochastic optimization.

Spectral-factorized Positive-definite Curvature Learning for NN Training Adaptive subgradient methods for online learning and stochastic optimization

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.291223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c9def5e-bff6-46b8-95d2-e17d763db378 · outbound

This paper cites Proposal of distance-weighted exponential natural evolution strategies.

Spectral-factorized Positive-definite Curvature Learning for NN Training Proposal of distance-weighted exponential natural evolution strategies

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.276055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0032d898-44e8-4844-ac23-fd404ffc5334 · outbound

This paper cites Exponential natural evolution strategies.

Spectral-factorized Positive-definite Curvature Learning for NN Training Exponential natural evolution strategies

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.263452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9f1f57e1-317d-4c0c-bf4b-460f4d558ec2 · outbound

This paper cites Natural gradient variational bayes without fisher matrix analytic calculation and its inversion.

Spectral-factorized Positive-definite Curvature Learning for NN Training Natural gradient variational bayes without fisher matrix analytic calculation and its inversion

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.250263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e790a1eb-1253-405d-997c-947d814fdca2 · outbound

This paper cites Shampoo: Preconditioned Stochastic Tensor Optimization.

Spectral-factorized Positive-definite Curvature Learning for NN Training Shampoo: Preconditioned Stochastic Tensor Optimization

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.235652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 88f86604-c7b3-4cdf-8260-90fe4f59457c · outbound

This paper cites K., and Gao, J.

Spectral-factorized Positive-definite Curvature Learning for NN Training K., and Gao, J

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.220656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0325d712-d2ca-416d-9fd0-a2cca310a9f0 · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:23.207351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 51c93680-6c3b-423e-b9c2-a43edafc0d98 · outbound

This paper cites NanoGPT (124M) quality in 8.2 minutes.

Spectral-factorized Positive-definite Curvature Learning for NN Training NanoGPT (124M) quality in 8.2 minutes

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.194031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0420da59-06ca-480c-a840-2934fa01f6e0 · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:23.181442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f9198895-69b4-44fa-8451-9c31d68ea10a · outbound

This paper cites E., Nielsen, D., Tangkaratt, V., Lin, W., Gal, Y., and Srivastava, A.

Spectral-factorized Positive-definite Curvature Learning for NN Training E., Nielsen, D., Tangkaratt, V., Lin, W., Gal, Y., and Srivastava, A

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.168820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7d6f67c1-0f70-42e0-8834-5a282c5d637d · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.212989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4384aed9-b1f8-4916-ad05-f0096188c627 · outbound

This paper cites Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport.

Spectral-factorized Positive-definite Curvature Learning for NN Training Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:15:22.674597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cbfbca9e-dfc5-4ef3-a529-b9b8bbd460f7 · outbound

This paper cites Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks.

Spectral-factorized Positive-definite Curvature Learning for NN Training Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.222585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fe15b20-d4c3-491c-b669-5e12e9c1e2c5 · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.228099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9701ce43-72f9-4f7c-8846-a2c03c91fe3c · outbound

This paper cites Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform.

Spectral-factorized Positive-definite Curvature Learning for NN Training Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.232002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f07db2-312e-47bd-a7d3-01dee2f00a43 · outbound

This paper cites Preconditioned stochastic gradient descent.

Spectral-factorized Positive-definite Curvature Learning for NN Training Preconditioned stochastic gradient descent

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.236153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d85c4705-1f8e-47c2-96a6-e4211c2f6226 · outbound

This paper cites E., and Schmidt, M.

Spectral-factorized Positive-definite Curvature Learning for NN Training E., and Schmidt, M

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.129381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 221cef9f-1fe2-4649-8cfb-ad280f9f81bd · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:23.116766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation df6dda30-82db-4525-8555-8b6a24361d51 · outbound

This paper cites M., and Schmidt, M.

Spectral-factorized Positive-definite Curvature Learning for NN Training M., and Schmidt, M

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.104451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3fcaa1b1-fb2c-484d-bf17-2aaaa7df3e02 · outbound

This paper cites E., and Schmidt, M.

Spectral-factorized Positive-definite Curvature Learning for NN Training E., and Schmidt, M

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.092126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dcb09d83-3130-494d-8a13-281bf898245e · outbound

This paper cites E., and Makhzani, A.

Spectral-factorized Positive-definite Curvature Learning for NN Training E., and Makhzani, A

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.080428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d1ff73d5-fed1-4f72-bc32-107140871d21 · outbound

This paper cites Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training.

Spectral-factorized Positive-definite Curvature Learning for NN Training Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.263627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3e3da1-5d1d-49f0-a52a-472240fdd597 · outbound

This paper cites M., Paull, L., Xiong, L., Song, L., and Weller, A.

Spectral-factorized Positive-definite Curvature Learning for NN Training M., Paull, L., Xiong, L., Song, L., and Weller, A

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.067863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 71b17889-1f39-4b49-91d1-1374354c56a8 · outbound

This paper cites Optimizing millions of hyperparameters by implicit differentiation.

Spectral-factorized Positive-definite Curvature Learning for NN Training Optimizing millions of hyperparameters by implicit differentiation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.054950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 40b8ec48-0b30-4e23-92ae-559af5f0822d · outbound

This paper cites Decoupled Weight Decay Regularization.

Spectral-factorized Positive-definite Curvature Learning for NN Training Decoupled Weight Decay Regularization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.275513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a7781b-536f-4795-bcc0-f136e6b7a69f · outbound

This paper cites Lecture Notes: Mathematical Modelling of DNA.

Spectral-factorized Positive-definite Curvature Learning for NN Training Lecture Notes: Mathematical Modelling of DNA

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.041692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 48c1f793-94a8-4f7b-bbab-9770694628fb · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:23.028316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ae16ffee-619a-49b2-9cd7-e227a5a31cc6 · outbound

This paper cites and Grosse, R.

Spectral-factorized Positive-definite Curvature Learning for NN Training and Grosse, R

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.012780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f17a77a8-3322-4558-8a8c-fddbf8951010 · outbound

This paper cites Mixed precision training.

Spectral-factorized Positive-definite Curvature Learning for NN Training Mixed precision training

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:23.001186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 58f6880a-ca02-4bd0-bce6-3ff394159dfa · outbound

This paper cites and Archambeau, C.

Spectral-factorized Positive-definite Curvature Learning for NN Training and Archambeau, C

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.987915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f8ae8b2c-a2cb-4e82-867c-0c4d73fb565c · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:22.975280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 57ca8511-4dd2-41aa-a0ea-253a2fb68655 · outbound

This paper cites B., Pedersen, M.

Spectral-factorized Positive-definite Curvature Learning for NN Training B., Pedersen, M

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.962144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c1a29769-998a-4b1b-98f4-5188fa456bef · outbound

This paper cites Controlling text-to-image diffusion by orthogonal finetuning.

Spectral-factorized Positive-definite Curvature Learning for NN Training Controlling text-to-image diffusion by orthogonal finetuning

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.950305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4910e34a-e02b-4c1e-9156-c94d82b65170 · outbound

This paper cites and Goldfarb, D.

Spectral-factorized Positive-definite Curvature Learning for NN Training and Goldfarb, D

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.938132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d4d9bc23-e920-4c46-a91a-4351ef49f056 · outbound

This paper cites Topmoumoute online natural gradient algorithm.

Spectral-factorized Positive-definite Curvature Learning for NN Training Topmoumoute online natural gradient algorithm

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.924444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0bed36cc-740f-4e70-a97f-9e59a8bb8767 · outbound

This paper cites Hiera: A hierarchical vision transformer without the bells-and-whistles.

Spectral-factorized Positive-definite Curvature Learning for NN Training Hiera: A hierarchical vision transformer without the bells-and-whistles

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.911091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 25ae04b8-a9d5-4a3b-8dc3-e035189877dd · outbound

This paper cites Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models.

Spectral-factorized Positive-definite Curvature Learning for NN Training Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.896822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94265aaf-654f-43e5-9518-debed1819096 · outbound

This paper cites Variational Learning is Effective for Large Deep Networks.

Spectral-factorized Positive-definite Curvature Learning for NN Training Variational Learning is Effective for Large Deep Networks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.332674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ee00b1-8cf5-4761-bc55-477f7dd8b99e · outbound

This paper cites A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale.

Spectral-factorized Positive-definite Curvature Learning for NN Training A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.336710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 508c6753-bc7d-4df4-b82f-bf397a2db88c · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:22.883048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b52138f-430a-4a20-8762-1113f292dde4 · outbound

This paper cites Analytic natural gradient updates for Cholesky factor in Gaussian variational approximation.

Spectral-factorized Positive-definite Curvature Learning for NN Training Analytic natural gradient updates for Cholesky factor in Gaussian variational approximation

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:15:22.573647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83b96c36-73e7-493c-9ee5-199a5e93837b · outbound

This paper cites and Hinton, G.

Spectral-factorized Positive-definite Curvature Learning for NN Training and Hinton, G

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.868880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bf389409-905e-4f2b-a8f6-243ac71fec16 · outbound

This paper cites H., and Nguyen, D.

Spectral-factorized Positive-definite Curvature Learning for NN Training H., and Nguyen, D

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.855781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9ce8ecdc-9a00-49d0-9a2d-df1e63d66bc5 · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:15:22.842598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fbacb41b-212c-40d6-99bf-708bc6ee40dc · outbound

This paper cites Invariance properties of the natural gradient in overparametrised systems.

Spectral-factorized Positive-definite Curvature Learning for NN Training Invariance properties of the natural gradient in overparametrised systems

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.827737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 44adf111-4888-4f8c-8bff-40c19ff7da16 · outbound

This paper cites SOAP: Improving and Stabilizing Shampoo using Adam.

Spectral-factorized Positive-definite Curvature Learning for NN Training SOAP: Improving and Stabilizing Shampoo using Adam

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.366670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d049ff4-1172-42c2-9bef-ab7c8f335e17 · outbound

This paper cites Natural evolution strategies.

Spectral-factorized Positive-definite Curvature Learning for NN Training Natural evolution strategies

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.813559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c2691899-b9fb-41bb-bee3-a8b33a115cd4 · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.374922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf0e4f03-f66b-4ce9-957c-5496a186889b · outbound

This paper cites J., Chun, S., Choe, J., and Yoo, Y.

Spectral-factorized Positive-definite Curvature Learning for NN Training J., Chun, S., Choe, J., and Yoo, Y

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.379246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaa2e5af-25a1-43c2-acb9-f5c52582ef4d · outbound

This paper cites Noisy natural gradient as variational inference.

Spectral-factorized Positive-definite Curvature Learning for NN Training Noisy natural gradient as variational inference

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:15:22.782559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a6bc752-0ecb-4ebb-8765-4616954ef9ef · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Spectral-factorized Positive-definite Curvature Learning for NN Training mixup: Beyond Empirical Risk Minimization

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.387966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b8b188b-e946-4551-9ced-bbb0eb046cee · outbound

This paper cites P., Veit, A., Kim, S., Reddi, S., Kumar, S., and Sra, S.

Spectral-factorized Positive-definite Curvature Learning for NN Training P., Veit, A., Kim, S., Reddi, S., Kumar, S., and Sra, S

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.393216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01a9f2a-5a2d-4ef5-a118-3ce50a59f375 · outbound

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

Spectral-factorized Positive-definite Curvature Learning for NN Training Why Transformers Need Adam: A Hessian Perspective

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.397282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5997082-c6bd-435a-b92c-8f8bae59f180 · outbound

This paper cites @esa (Ref.

Spectral-factorized Positive-definite Curvature Learning for NN Training @esa (Ref

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.402681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c5288ed-3836-4da0-8208-9d84eabb415d · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.409213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33f15f5c-6b30-48d6-8348-f68aa9ea2d46 · outbound

This paper cites an unresolved cited work.

Spectral-factorized Positive-definite Curvature Learning for NN Training Unresolved cited work

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T16:15:07.414107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers