Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average RewardHairi FNUJia Liuet al.2022ICLR 2022
Understanding latent correlation-based multiview learning and self-supervision: An identifiability perspectiveQi LyuXiao Fuet al.2022ICLR 2022
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement LearningXin ZhangZhuqing Liuet al.2021NeurIPS 2021
Nonconvex Min-Max Bilevel Optimization for Task Robust Meta LearningAlex GuSongtao Luet al.2021ICML 2021
Federated acoustic modeling for automatic speech recognitionXiaodong CuiSongtao Luet al.2021ICASSP 2021
Training logical neural networks by primal-dual methods for neuro-symbolic reasoningSongtao LuNaweed Khanet al.2021ICASSP 2021
On the convergence of randomized Bregman coordinate descent for non-Lipschitz composite problemsTianxiang GaoSongtao Luet al.2021ICASSP 2021
Achieving Channel Capacity of Visible Light CommunicationShuai MaRuixin Yanget al.2021IEEE Systems Journal
Adversarial Data Augmentation Improves Unsupervised Machine LearningChia-Yi HsuPin-Yu Chenet al.2021ICLR 2021
Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex OptimizationZichong LiPin-Yu Chenet al.2021AISTATS 2021