|
Poster
|
Thu 10:30 |
Learning Curves for SGD on Structured Features Blake Bordelon · Cengiz Pehlevan |
|
|
Poster
|
Tue 18:30 |
Strength of Minibatch Noise in SGD Liu Ziyin · Kangqiao Liu · Takashi Mori · Masahito Ueda |
|
|
Poster
|
Wed 10:30 |
Assessing Generalization of SGD via Disagreement Yiding Jiang · Vaishnavh Nagarajan · Christina Baek · Zico Kolter |
|
|
Poster
|
Mon 2:30 |
Hybrid Local SGD for Federated Learning with Heterogeneous Communications Yuanxiong Guo · Ying Sun · Rui Hu · Yanmin Gong |
|
|
Poster
|
Tue 18:30 |
Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank? Sheikh Shams Azam · Seyyedali Hosseinalipour · Qiang Qiu · Christopher Brinton |
|
|
Spotlight
|
Tue 18:30 |
Strength of Minibatch Noise in SGD Liu Ziyin · Kangqiao Liu · Takashi Mori · Masahito Ueda |
|
|
Poster
|
Tue 10:30 |
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits Yan Li · Dhruv Choudhary · Xiaohan Wei · Baichuan Yuan · Bhargav Bhushanam · Tuo Zhao · Guanghui Lan |
|
|
Poster
|
Mon 10:30 |
Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise Xingyu Wang · Sewoong Oh · Chang-Han Rhee |
|
|
Spotlight
|
Mon 2:30 |
Hybrid Local SGD for Federated Learning with Heterogeneous Communications Yuanxiong Guo · Ying Sun · Rui Hu · Yanmin Gong |
|
|
Poster
|
Thu 18:30 |
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications Ziqiao Wang · Yongyi Mao |
|
|
Poster
|
Mon 18:30 |
Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum Kirby Banman · Garnet Liam Peet-Pare · Nidhi Hegde · Alona Fyshe · Martha White |
|
|
Spotlight
|
Wed 18:30 |
SGD Can Converge to Local Maxima Liu Ziyin · Botao Li · James Simon · Masahito Ueda |