Saved in:
Bibliographic Details
Main Authors: Jia, Zhichao, Lan, Guanghui, Zhang, Zhe
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15368
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910762268622848
author Jia, Zhichao
Lan, Guanghui
Zhang, Zhe
author_facet Jia, Zhichao
Lan, Guanghui
Zhang, Zhe
contents Convex risk measures play a foundational role in the area of stochastic optimization. However, in contrast to risk neutral models, their applications are still limited due to the lack of efficient solution methods. In particular, the mean $L_p$ semi-deviation is a classic risk minimization model, but its solution is highly challenging due to the composition of concave-convex functions and the lack of uniform Lipschitz continuity. In this paper, we discuss some progresses on the design of efficient algorithms for $L_p$ risk minimization, including a novel lifting reformulation to handle the concave-convex composition, and a new stochastic approximation method to handle the non-Lipschitz continuity. We establish an upper bound on the sample complexity associated with this approach and show that this bound is not improvable for $L_p$ risk minimization in general through the construction of a nearly matching lower complexity bound.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15368
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nearly Optimal $L_p$ Risk Minimization
Jia, Zhichao
Lan, Guanghui
Zhang, Zhe
Optimization and Control
Convex risk measures play a foundational role in the area of stochastic optimization. However, in contrast to risk neutral models, their applications are still limited due to the lack of efficient solution methods. In particular, the mean $L_p$ semi-deviation is a classic risk minimization model, but its solution is highly challenging due to the composition of concave-convex functions and the lack of uniform Lipschitz continuity. In this paper, we discuss some progresses on the design of efficient algorithms for $L_p$ risk minimization, including a novel lifting reformulation to handle the concave-convex composition, and a new stochastic approximation method to handle the non-Lipschitz continuity. We establish an upper bound on the sample complexity associated with this approach and show that this bound is not improvable for $L_p$ risk minimization in general through the construction of a nearly matching lower complexity bound.
title Nearly Optimal $L_p$ Risk Minimization
topic Optimization and Control
url https://arxiv.org/abs/2407.15368