arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.04658stat.MLcs.LG
收藏

近似拒绝采样的样本复杂度及其在平滑在线学习中的应用

The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learning

MIT(麻省理工学院)

Adam Block, Yury Polyanskiy

AI总结:

本文刻画了在有界 f-散度条件下近似拒绝采样的最优样本复杂度,并将其应用于放宽对手约束的平滑在线学习场景,同时比较了重要性采样与拒绝采样的效果。

摘要:

假设我们可以获取来自分布 μ 的 n 个独立样本,并希望输出其中一个样本,目标是使输出分布尽可能接近目标分布 ν。在这项工作中,我们证明了在所有满足有界 f-散度 D_f(ν‖μ) ≤ D 的分布对 (ν, μ) 类别上,作为 n 的函数的最优总变差距离由 $\ ildeΘ(\ rac{D}{f'(n)})$ 给出。此前,该问题仅在 ν 关于 μ 的 Radon-Nikodym 导数一致有界的情形下被研究过。随后,我们考虑了该结果在一个看似截然不同的领域——平滑在线学习——中的应用,并证明了近期关于极小极大遗憾和预言机高效算法遗憾的结果,即使在对手的约束被放宽(具有有界 f-散度,而非有界 Radon-Nikodym 导数)的情况下仍然成立。最后,我们还研究了重要性采样在函数类上均值估计一致性问题中的有效性,并将重要性采样与拒绝采样进行了比较。

英文摘要:

Suppose we are given access to $n$ independent samples from distribution $μ$ and we wish to output one of them with the goal of making the output distributed as close as possible to a target distribution $ν$. In this work we show that the optimal total variation distance as a function of $n$ is given by $\tildeΘ(\frac{D}{f'(n)})$ over the class of all pairs $ν,μ$ with a bounded $f$-divergence $D_f(ν\|μ)\leq D$. Previously, this question was studied only for the case when the Radon-Nikodym derivative of $ν$ with respect to $μ$ is uniformly bounded. We then consider an application in the seemingly very different field of smoothed online learning, where we show that recent results on the minimax regret and the regret of oracle-efficient algorithms still hold even under relaxed constraints on the adversary (to have bounded $f$-divergence, as opposed to bounded Radon-Nikodym derivative). Finally, we also study efficacy of importance sampling for mean estimates uniform over a function class and compare importance sampling with rejection sampling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑