Improving the sample and communication complexity for decentralized non-convex optimization: Joint gradient estimation and trackingHaoran SunSongtao Luet al.2020ICML 2020
Safe reinforcement learning in constrained markov decision processesAkifumi WachiYanan Sui2020ICML 2020
Unsupervised speech decomposition via triple information bottleneckKaizhi QianYang Zhanget al.2020ICML 2020
Stochastic gauss-newton algorithms for nonconvex compositional optimizationQuoc Tran-DinhNhan H. Phamet al.2020ICML 2020
Is there a trade-off between fairness and accuracy? A perspective using mismatched hypothesis testingSanghamitra DuttaDennis Weiet al.2020ICML 2020
PoWER-BERT: Accelerating BERT inference via progressive word-vector eliminationSaurabh GoyalAnamitra R. Choudhuryet al.2020ICML 2020
Min-max optimization without gradients: Convergence and applications to black-box evasion and poisoning attacksSijia LiuSongtao Luet al.2020ICML 2020
Enhancing simple models by exploiting what they already knowAmit DhurandharKarthikeyan Shanmugamet al.2020ICML 2020