Obserwuj
Junchi Yang
Junchi Yang
Chinese University of Hong Kong, Shenzhen
Zweryfikowany adres z cuhk.edu.cn - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Global convergence and variance reduction for a class of nonconvex-nonconcave minimax problems
J Yang, N Kiyavash, N He
Advances in Neural Information Processing Systems 33, 1153-1165, 2020
206*2020
The complexity of nonconvex-strongly-concave minimax optimization
S Zhang*, J Yang*, C Guzmán, N Kiyavash, N He
Uncertainty in Artificial Intelligence, 482-492, 2021
842021
Faster single-loop algorithms for minimax optimization without strong concavity
J Yang, A Orvieto, A Lucchi, N He
International Conference on Artificial Intelligence and Statistics, 5485-5517, 2022
692022
A catalyst framework for minimax optimization
J Yang, S Zhang, N Kiyavash, N He
Advances in Neural Information Processing Systems 33, 5667-5678, 2020
672020
Nest your adaptive algorithm for parameter-agnostic nonconvex minimax optimization
J Yang*, X Li*, N He
Advances in Neural Information Processing Systems, 2022
262022
Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
J Yang*, X Li*, I Fatkhullin, N He
Thirty-seventh Conference on Neural Information Processing Systems, 2023
202023
Parameter-agnostic optimization under relaxed smoothness
F Hübler, J Yang, X Li, N He
International Conference on Artificial Intelligence and Statistics, 4861-4869, 2024
182024
TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
X Li, J Yang, N He
International Conference on Learning Representations, 2023
82023
Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
L Zhang*, J Yang*, A Karbasi, N He
Advances in Neural Information Processing Systems, 2023
42023
Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps
J Yang, M Yildirim, Q Feng
arXiv preprint arXiv:2407.02689, 2024
2024
Towards Near-Optimal and Adaptive Algorithms in Minimax Optimization
J Yang
ETH Zurich, 2023
2023
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–11