1
Mean-based algorithms: A lower bound and regret
均值算法理论突破，揭示其下界与遗憾的互补关系。
arXiv:2606.04931v1 Announce Type: new Abstract: Mean-based algorithms are a class of online learning algorithms that assign low probability to actions…
2
Stabilizing Policy Optimization via Logits Convexity
新论文提出通过logits凸性稳定策略优化，为强化学习训练提供理论新视角。
arXiv:2603.00963v2 Announce Type: replace Abstract: While reinforcement learning (RL) has been central to the recent success of large language models …
3
Proximal basin hopping: global optimization with guarantees
首次为全局优化问题提供理论保证的Proximal basin hopping算法，打破传统纯启发式方法局限
arXiv:2605.18364v1 Announce Type: new Abstract: Global optimization is a challenging problem, with plenty of algorithms displaying empirical success, …