NeurIPS 2022 Workshop OPT Submissions

A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
Jiaxin Shi, Lester Mackey
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Data-heterogeneity-aware Mixing for Decentralized Learning
Yatin Dandi, Anastasia Koloskova, Martin Jaggi, Sebastian U Stich
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Rieoptax: Riemannian Optimization in JAX
Saiteja Utpala, Andi Han, Pratik Jawanpuria, Bamdev Mishra
- Published: 23 Nov 2022, Last Modified: 07 Apr 2024
- OPT 2022 Poster
- Readers: Everyone
TorchOpt: An Efficient Library for Differentiable Optimization
Jie Ren, Xidong Feng, Bo Liu, Xuehai Pan, Yao Fu, Luo Mai, Yaodong Yang
- Published: 23 Nov 2022, Last Modified: 07 Apr 2024
- OPT 2022 Poster
- Readers: Everyone
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data
Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, Christos Thrampoulidis
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Rethinking Sharpness-Aware Minimization as Variational Inference
Szilvia Ujváry, Zsigmond Telek, Anna Kerekes, Anna Mészáros, Ferenc Huszár
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
Xiang Li, Junchi YANG, Niao He
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Toward Understanding Why Adam Converges Faster Than SGD for Transformers
Yan Pan, Yuanzhi Li
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Bidirectional Adaptive Communication for Heterogeneous Distributed Learning
Dmitrii Avdiukhin, Vladimir Braverman, Nikita Ivkin, Sebastian U Stich
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
How Does Sharpness-Aware Minimization Minimizes Sharpness?
Kaiyue Wen, Tengyu Ma, Zhiyuan Li
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Oral
- Readers: Everyone
Strong Lottery Ticket Hypothesis with $\epsilon$–perturbation
Fangshuo Liao, Zheyang Xiong, Anastasios Kyrillidis
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Oral
- Readers: Everyone
Optimization for Robustness Evaluation beyond ℓp Metrics
Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A Erdogdu
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Nesterov Meets Optimism: Rate-Optimal Optimistic-Gradient-Based Method for Stochastic Bilinearly-Coupled Minimax Optimization
Chris Junchi Li, Angela Yuan, Gauthier Gidel, Michael Jordan
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Distributed Online and Bandit Convex Optimization
Kumar Kshitij Patel, Aadirupa Saha, Lingxiao Wang, Nathan Srebro
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
On Convexity and Linear Mode Connectivity in Neural Networks
David Yunis, Kumar Kshitij Patel, Pedro Henrique Pamplona Savarese, Gal Vardi, Jonathan Frankle, Matthew Walter, Karen Livescu, Michael Maire
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks
Xinmeng Huang, Kun Yuan
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Target-based Surrogates for Stochastic Optimization
Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad Harikandeh, Mark Schmidt, Nicolas Le Roux
- Published: 23 Nov 2022, Last Modified: 07 Apr 2024
- OPT 2022 Poster
- Readers: Everyone
Why (and When) does Local SGD Generalize Better than SGD?
Xinran Gu, Kaifeng Lyu, Longbo Huang, Sanjeev Arora
- Published: 23 Nov 2022, Last Modified: 07 Apr 2024
- OPT 2022 Poster
- Readers: Everyone
Momentum Extragradient is Optimal for Games with Cross-Shaped Spectrum
Junhyung Lyle Kim, Gauthier Gidel, Anastasios Kyrillidis, Fabian Pedregosa
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Stochastic Adaptive Regularization Method with Cubics: A High Probability Complexity Bound
Katya Scheinberg, Miaolan Xie
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
ProxSkip for Stochastic Variational Inequalities: A Federated Learning Algorithm for Provable Communication Acceleration
Siqi Zhang, Nicolas Loizou
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
DIMENSION-REDUCED ADAPTIVE GRADIENT METHOD
Jingyang Li, Pan Zhou, Kuangyu Ding, Kim-Chuan Toh, Yinyu Ye
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Fast Convergence of Greedy 2-Coordinate Updates for Optimizing with an Equality Constraint
Amrutha Varshini Ramesh, Aaron Mishkin, Mark Schmidt
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Quadratic minimization: from conjugate gradients to an adaptive heavy-ball method with Polyak step-sizes
Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone