arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2405.03219math.OC
收藏

为随机鞍点问题提供高概率保证的一般程序

General Procedure to Provide High-Probability Guarantees for Stochastic Saddle Point Problems

Dongyang Li, Haobin Li, Junyu Zhang

AI总结:

本文研究SC-SC随机鞍点问题,提出一般PB-SSP框架,仅以对数次预言机调用即可高概率获得小对偶间隙解,应用于SAA预言机时还改进了样本复杂度。

摘要:

本文考虑光滑强凸和强凹(SC-SC)随机鞍点(SSP)问题。假设存在任意预言机,在期望意义上返回某种间隙意义下的 $ε$-解,该间隙可以是对偶间隙或其较弱变体。我们提出一般的 PB-SSP 框架,仅通过 $\mathcal{O}\big(\log \frac{1}{p}\cdot\text{poly}(\log κ)\big)$ 次该预言机调用,以高概率保证 $ε$ 小的对偶间隙解,其中 $p\in(0,1)$ 为置信水平,$κ$ 为条件数。应用于样本平均近似(SAA)预言机时,除赋予解高概率外,由于高概率论证使我们能规避 SAA 一致稳定性分析的关键困难,甚至将样本复杂度改进 $\text{poly}(κ)$ 倍。

英文摘要:

This paper considers smooth strongly convex and strongly concave (SC-SC) stochastic saddle point (SSP) problems. Suppose there is an arbitrary oracle that in expectation returns an $ε$-solution in the sense of certain gaps, which can be the duality gap or its weaker variants. We propose a general PB-SSP framework to guarantee an $ε$ small duality gap solution with high probability via only $\mathcal{O}\big(\log \frac{1}{p}\cdot\text{poly}(\log κ)\big)$ calls of this oracle, where $p\in(0,1)$ is the confidence level and $κ$ is the condition number. When applied to the sample average approximation (SAA) oracle, in addition to equipping the solution with high probability, our approach even improves the sample complexity by a factor of $\text{poly}(κ)$, since the high-probability argument enables us to circumvent some key difficulties of the uniform stability analysis of SAA.

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。

↑