Risk-Averse Learning with Varying Risk Levels

TL;DR

This paper develops risk-averse online optimization algorithms that adapt to changing risk levels in dynamic environments, using CVaR as the risk measure, with theoretical regret bounds and numerical validation.

Contribution

It introduces a novel risk-level variation metric and provides algorithms with regret analysis for both first- and zeroth-order settings in non-stationary environments.

Findings

Algorithms achieve sublinear regret bounds.

Methods adapt effectively to risk level changes.

Numerical experiments confirm theoretical results.

Abstract

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.