( en | de | ru )

 

Disambiguation

From post

копироватьудалитьдобавить публикацию в буфер
Why (and When) does Local SGD Generalize Better than SGD?

, , , и . ICLR, OpenReview.net, (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

Kaifeng Jin

Siwei Lyu

Siwei Lyu

Yong-Sang Lyu

Anatoliy Lyubar

 

Другие публикации лиц с тем же именем

Gradient Descent Maximizes the Margin of Homogeneous Neural Networks., и . ICLR, OpenReview.net, (2020)Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing., , , , и . ICML, том 202 из Proceedings of Machine Learning Research, стр. 15200-15238. PMLR, (2023)Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate., , и . NeurIPS, (2020)Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias., , , и . NeurIPS, стр. 12978-12991. (2021)On the SDEs and Scaling Rules for Adaptive Gradient Algorithms., , , и . NeurIPS, (2022)Single-Source Bottleneck Path Algorithm Faster than Sorting for Sparse Graphs., , и . ICALP, том 107 из LIPIcs, стр. 43:1-43:14. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, (2018)Fine-grained Complexity Meets IP = PSPACE., , , , и . SODA, стр. 1-20. SIAM, (2019)Why (and When) does Local SGD Generalize Better than SGD?, , , и . ICLR, OpenReview.net, (2023)Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking., , , , , и . ICLR, OpenReview.net, (2024)A Quadratic Synchronization Rule for Distributed Deep Learning., , , , и . ICLR, OpenReview.net, (2024)