|
Spotlight
|
Wed 7:30
|
Towards understanding how momentum improves generalization in deep learning
Samy Jelassi · Yuanzhi Li
|
|
|
Poster
|
Wed 15:30
|
Deep equilibrium networks are sensitive to initialization statistics
Atish Agarwala · Samuel Schoenholz
|
|
|
Spotlight
|
Wed 7:40
|
Deep equilibrium networks are sensitive to initialization statistics
Atish Agarwala · Samuel Schoenholz
|
|
|
Poster
|
Wed 15:30
|
Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications
Bokun Wang · Tianbao Yang
|
|
|
Spotlight
|
Wed 8:10
|
Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications
Bokun Wang · Tianbao Yang
|
|
|
Poster
|
Wed 15:30
|
Towards Understanding Sharpness-Aware Minimization
Maksym Andriushchenko · Nicolas Flammarion
|
|
|
Spotlight
|
Wed 14:55
|
Towards Understanding Sharpness-Aware Minimization
Maksym Andriushchenko · Nicolas Flammarion
|
|
|
Poster
|
Wed 15:30
|
Extended Unconstrained Features Model for Exploring Deep Neural Collapse
Tom Tirer · Joan Bruna
|
|
|
Spotlight
|
Wed 8:50
|
Extended Unconstrained Features Model for Exploring Deep Neural Collapse
Tom Tirer · Joan Bruna
|
|
|
Poster
|
Tue 15:30
|
Power-Law Escape Rate of SGD
Takashi Mori · Liu Ziyin · Kangqiao Liu · Masahito Ueda
|
|
|
Spotlight
|
Tue 11:10
|
Power-Law Escape Rate of SGD
Takashi Mori · Liu Ziyin · Kangqiao Liu · Masahito Ueda
|
|
|
Poster
|
Wed 15:30
|
Optimal Algorithms for Stochastic Multi-Level Compositional Optimization
Wei Jiang · Bokun Wang · Yibo Wang · Lijun Zhang · Tianbao Yang
|
|
