4 papers
Parameter-free Algorithms for the Stochastically Extended Adversarial Model
Shuche Wang, Adarsh Barik, Peng Zhao +1
We develop the first parameter-free algorithms for the Stochastically Extended Adversarial (SEA) model, a framework that bridges adversarial and stochastic online convex optimizati…
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
Wenfeng Feng, Penghong Zhao, Guochao Jiang +4
Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely he…
Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
Yu-Jie Zhang, Sheng-An Xu, Peng Zhao +1
We study the generalized linear bandit (GLB) problem, a contextual multi-armed bandit framework that extends the classical linear model by incorporating a non-linear link function,…
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
Yu-Jie Zhang, Peng Zhao, Masashi Sugiyama
Non-stationary online learning has drawn much attention in recent years. Despite considerable progress, dynamic regret minimization has primarily focused on convex functions, leavi…