2610.21870R·cs.LG15 de out. de 2026Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents Hanzhen Wang, Boxiang Lyu, Zhongxiang Dai, Siyang Gao, Dake Zhang, Shuang Qiu
2609.20327R·math.OC18 de set. de 2026Near-Optimal Pure Single-Loop Extragradient Method for Strongly Convex--Strongly Concave Minimax Optimization Minhao Zhang , Zi Xu
2609.18656R·cs.LG17 de set. de 2026Revisiting Distributed Sign-Based Variance Reduction Wei Jiang , Zechao Li , Lijun Zhang
2609.18416R·math.OC17 de set. de 2026Gradient Descent with Stochastic Subspaces via Persistence of Memory Subhroshekhar Ghosh , Clement Z. Q. Ng , Pierre-Louis Poirion , Akiko Takeda
2609.17973R·math.OC17 de set. de 2026Matching Multi-Loop Complexities with a Single Loop: Optimal Optimization Stationarity and Best-Known Game Stationarity in Nonconvex--Concave Minimax Optimization Minghao Zhang , Zi Xu