arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.02313math.OCcs.LGcs.SYeess.SY
收藏

具有决策依赖分布的随机鞍点问题

Stochastic Saddle Point Problems with Decision-Dependent Distributions

University of Colorado(科罗拉多大学)

Killian Wood, Emiliano Dall'Anese

摘要:

本文主要研究决策相依分布的随机鞍点问题。这些问题的目标是随机支付函数的期望值,其数据分布会随着决策变量的变化而漂移,这是一种由分布图表示的现象。适应分布变化的一种常见方法是,一旦发现新的分布,就重新训练最佳决策,或者重复训练。我们引入平衡点的概念,这是这个重复的再训练过程的不动点,并提供充分条件,他们的存在性和唯一性。为了找到平衡点,我们开发了确定性和随机原始对偶法,并证明了它们的收敛性与常数步长在前者和多项式衰减步长时间表在后者。通过将随机梯度估计的误差建模为子威布尔随机变量,我们提供了每次迭代的期望误差界和高概率误差界。在没有分布图的额外知识的情况下,计算鞍点是棘手的。因此,我们提出了一个条件的分布图-我们称之为反对混合优势-确保目标是强凸-强凹。最后,我们证明了一个单一的功能评估的衍生自由算法是能够近似鞍点

英文摘要:

This paper focuses on stochastic saddle point problems with decision-dependent distributions. These are problems whose objective is the expected value of a stochastic payoff function and whose data distribution drifts in response to decision variables--a phenomenon represented by a distributional map. A common approach to accommodating distributional shift is to retrain optimal decisions once a new distribution is revealed, or repeated retraining. We introduce the notion of equilibrium points, which are the fixed points of this repeated retraining procedure, and provide sufficient conditions for their existence and uniqueness. To find equilibrium points, we develop deterministic and stochastic primal-dual algorithms and demonstrate their convergence with constant step-size in the former and polynomial decay step-size schedule in the latter. By modeling errors emerging from a stochastic gradient estimator as sub-Weibull random variables, we provide error bounds in expectation and in high probability that hold for each iteration. Without additional knowledge of the distributional map, computing saddle points is intractable. Thus we propose a condition on the distributional map--which we call opposing mixture dominance--that ensures that the objective is strongly-convex-strongly-concave. Finally, we demonstrate that derivative-free algorithms with a single function evaluation are capable of approximating saddle points

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。

↑