Online Convex Optimization
PulseAugur coverage of Online Convex Optimization — every cluster mentioning Online Convex Optimization across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
New Principle Achieves Optimal Online Inventory Optimization
Researchers have developed a novel principle for online inventory optimization (OIO) that achieves optimal performance on general convex sets. This method, which involves maintaining a hidden target and projecting it on…
-
New OCO Framework Improves Regret with Noisy Probes
Researchers have developed a new framework for Online Convex Optimization (OCO) that can improve worst-case regret even with a limited and noisy budget of pairwise probes. The proposed method unifies sublinear best-expe…
-
AI代理应对时间遗憾和动态优化挑战
两篇新研究论文探讨了改进AI代理决策和学习的先进方法。第一篇论文“Trivium”将时间遗憾作为因果记忆控制器的关键目标，旨在比基于结果的方法更有效地记录和纠正错误。第二篇论文“无参数动态遗憾”提出了一种新颖的在线凸优化算法，该算法处理时变移动成本、延迟反馈和记忆，从而实现了改进的动态遗憾界限。
-
新理论将多面体不稳定性与在线学习遗憾联系起来
研究人员开发了一个新的理论框架，用于理解涉及组合动作的在线学习问题中的遗憾。他们的工作引入了“多面体不稳定性”的概念，该概念量化了决策过程中活动区域的变化次数。这种不稳定性被证明可以决定遗憾率，并在现有的类似专家和依赖维度的界限之间进行插值。