1.2k citations
- Chinese Academy of SciencesCN258 papers
- University of Chinese Academy of SciencesCN112 papers
- University of Science and Technology of ChinaCN18 papers
- Peking UniversityCN13 papers
- Tencent (China)CN13 papers
- Tsinghua UniversityCN10 papers
- Beihang UniversityCN9 papers
- National University of SingaporeSG9 papers
- Microsoft Research Asia (China)CN8 papers
- Peng Cheng LaboratoryCN8 papers
- Institute of Information EngineeringCN6 papers
- Lenovo (China)CN6 papers
10 papers · 1 filter
Majorized Semi-proximal Alternating Coordinate Method for Nonsmooth Convex-Concave Minimax Optimization
Yu-Hong Dai, Jiani Wang, Liwei Zhang
Minimax optimization problems are an important class of optimization problems arising from modern machine learning and traditional research areas. While there have been many numeri…
Optimization with Least Constraint Violation
Yu-Hong Dai, Liwei Zhang
Study about theory and algorithms for constrained optimization usually assumes that the feasible region of the optimization problem is nonempty. However, there are many important p…
A variable metric mini-batch proximal stochastic recursive gradient algorithm with diagonal Barzilai-Borwein stepsize
Tengteng Yu, Xin-Wei Liu, Yu-Hong Dai +1
Variable metric proximal gradient methods with different metric selections have been widely used in composite optimization. Combining the Barzilai-Borwein (BB) method with a diagon…
Optimality Conditions for Constrained Minimax Optimization
Yu-HOng Dai, Liwei Zhang
Minimax optimization problems arises from both modern machine learning including generative adversarial networks, adversarial training and multi-agent reinforcement learning, as we…
On the acceleration of the Barzilai-Borwein method
Yakui Huang, Yu-Hong Dai, Xin-Wei Liu +1
The Barzilai-Borwein (BB) gradient method is efficient for solving large-scale unconstrained problems to the modest accuracy and has a great advantage of being easily extended to s…
Geometric Convergence for Distributed Optimization with Barzilai-Borwein Step Sizes
Juan Gao, Xinwei Liu, Yu-Hong Dai +2
We consider a distributed multi-agent optimization problem over a time-invariant undirected graph, where each agent possesses a local objective function and all agents collaborativ…