Risk-Averse Learning with Varying Risk Levels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Siyi, Wang, Zifan, Johansson, Karl H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917173322055680
author Wang, Siyi
Wang, Zifan
Johansson, Karl H.
author_facet Wang, Siyi
Wang, Zifan
Johansson, Karl H.
contents In safety-critical decision-making, the environment may evolve over time, and the learner adjusts its risk level accordingly. This work investigates risk-averse online optimization in dynamic environments with varying risk levels, employing Conditional Value-at-Risk (CVaR) as the risk measure. To capture the dynamics of the environment and risk levels, we employ the function variation metric and introduce a novel risk-level variation metric. Two information settings are considered: a first-order scenario, where the learner observes both function values and their gradients; and a zeroth-order scenario, where only function evaluations are available. For both cases, we develop risk-averse learning algorithms with a limited sampling budget and analyze their dynamic regret bounds in terms of function variation, risk-level variation, and the total number of samples. The regret analysis demonstrates the adaptability of the algorithms in non-stationary and risk-sensitive settings. Finally, numerical experiments are presented to demonstrate the efficacy of the methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22986
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Risk-Averse Learning with Varying Risk Levels
Wang, Siyi
Wang, Zifan
Johansson, Karl H.
Optimization and Control
Machine Learning
In safety-critical decision-making, the environment may evolve over time, and the learner adjusts its risk level accordingly. This work investigates risk-averse online optimization in dynamic environments with varying risk levels, employing Conditional Value-at-Risk (CVaR) as the risk measure. To capture the dynamics of the environment and risk levels, we employ the function variation metric and introduce a novel risk-level variation metric. Two information settings are considered: a first-order scenario, where the learner observes both function values and their gradients; and a zeroth-order scenario, where only function evaluations are available. For both cases, we develop risk-averse learning algorithms with a limited sampling budget and analyze their dynamic regret bounds in terms of function variation, risk-level variation, and the total number of samples. The regret analysis demonstrates the adaptability of the algorithms in non-stationary and risk-sensitive settings. Finally, numerical experiments are presented to demonstrate the efficacy of the methods.
title Risk-Averse Learning with Varying Risk Levels
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2512.22986