Problem
Research questions and friction points this paper is trying to address.
online learning
randomized proper learning algorithm
mistake bound
Littlestone dimension
Optimal Randomized Proper Online Learning
🤖 AI Summary
本文解决了在线学习函数类的最优预期错误界问题，通过随机化适当学习算法，将先前的界限改进至O(L(H)log T)，其中L(H)是Littlestone维度。
📝 Abstract
We prove that the optimal expected mistake bound of online learning a function class $\mathcal{H}$ by a randomized proper learning algorithm is $O(\mathtt{L}(\mathcal{H}) \log T)$, where $\mathtt{L}(\mathcal{H})$ is the Littlestone dimension of $\mathcal{H}$ and $T$ is the time horizon. Our result improves upon the previously best known bound of $O(\mathtt{L}(\mathcal{H}) \log^6 T)$ given by Daskalakis and Golowich (STOC 2022), and is optimal up to a universal constant for worst-case classes.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Optimal Expected Mistake Bound
Randomized Proper Learning Algorithm
Littlestone Dimension
🔎 Similar Papers
No similar papers found.
