paper-with-me

홈 › Papers

Learning with CVaR-based feedback under potentially heavy tails

2020-06-03 · Matthew J. Holland, El Mehdi Haress

We study learning algorithms that seek to minimize the conditional value-at-risk (CVaR), when all the learner knows is that the losses incurred may be heavy-tailed. We begin by studying a general-purpose estimator of CVaR for potentially heavy-tailed random variables, which is easy to implement in practice, and requires nothing more than finite variance and a distribution function that does not change too fast or slow around just the quantile of interest. With this estimator in hand, we then derive a new learning algorithm which robustly chooses among candidates produced by stochastic gradient-driven sub-processes. For this procedure we provide high-probability excess CVaR bounds, and to complement the theory we conduct empirical tests of the underlying CVaR estimator and the learning algorithm derived from it.

📄 PDF Abstract BibTeX arXiv:2006.02001

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the Generalization and Robustness in Conditional Value-at-Risk

2026-02-20 · Dinesh Karthik Mulumudi, Piyushi Manupriya, Gholamali Aminian, Anant Raj arxiv

Conditional Value-at-Risk (CVaR) is a widely used risk-sensitive objective for learning under rare but high-impact losses, yet its statistical behavior under heavy-tailed data remains poorly understood. Unlike expectatio…

Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions

2019-01-04 · ICML 2020 1 · Prashanth L. A., Krishna Jagannathan, Ravi Kumar Kolla

Conditional Value-at-Risk (CVaR) is a widely used risk metric in applications such as finance. We derive concentration bounds for CVaR estimates, considering separately the cases of light-tailed and heavy-tailed distribu…

Multi-Armed Bandits

Tail Annealing for Heavy-Tailed Flow Matching

2026-05-19 · Jean Pachebat arxiv

Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolating between heavy-tailed data and Gaussians is ill-posed. We propose a…

Robust variance-regularized risk minimization with concomitant scaling

2023-01-27 · Matthew J. Holland

Under losses which are potentially heavy-tailed, we consider the task of minimizing sums of the loss mean and standard deviation, without trying to accurately estimate the variance. By modifying a technique for variance-…

Optimal Best-Arm Identification Methods for Tail-Risk Measures

2020-08-17 · NeurIPS 2021 12 · Shubhada Agrawal, Wouter M. Koolen, Sandeep Juneja

Conditional value-at-risk (CVaR) and value-at-risk (VaR) are popular tail-risk measures in finance and insurance industries as well as in highly reliable, safety-critical uncertain environments where often the underlying…