# Adaptive Sampling for Stochastic Risk-Averse Learning

arXiv: https://arxiv.org/abs/1910.12511 · HTML: https://mlsanity.com/paper/1910.12511/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 30 of 39)

- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [Probable Domain Generalization via Quantile Risk Minimization](https://mlsanity.com/paper/2207.09944/) (2022)
- [Risk-Averse Offline Reinforcement Learning](https://mlsanity.com/paper/2102.05371/) (2021)
- [On Tilted Losses in Machine Learning: Theory and Applications](https://mlsanity.com/paper/2109.06141/) (2021)
- [Efficient Risk-Averse Reinforcement Learning](https://mlsanity.com/paper/2205.05138/) (2022)
- [Probabilistically Robust Learning: Balancing Average- and Worst-case Performance](https://mlsanity.com/paper/2202.01136/) (2022)
- [Off-Policy Risk Assessment in Contextual Bandits](https://mlsanity.com/paper/2104.08977/) (2021)
- [Rank-based Decomposable Losses in Machine Learning: A Survey](https://mlsanity.com/paper/2207.08768/) (2022)
- [Distributionally Robust Models with Parametric Likelihood Ratios](https://mlsanity.com/paper/2204.06340/) (2022)
- [Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond](https://mlsanity.com/paper/2212.13669/) (2022)
- [Distributionally Robust Optimization via Ball Oracle Acceleration](https://mlsanity.com/paper/2203.13225/) (2022)
- [Spectral risk-based learning using unbounded losses](https://mlsanity.com/paper/2105.04816/) (2021)
- [Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning](https://mlsanity.com/paper/2602.16796/) (2026)
- [Stochastic Optimization for Spectral Risk Measures](https://mlsanity.com/paper/2212.05149/) (2022)
- [Linear Bandits on Uniformly Convex Sets](https://mlsanity.com/paper/2103.05907/) (2021)
- [Risk-Aware Learning for Scalable Voltage Optimization in Distribution Grids](https://mlsanity.com/paper/2110.01490/) (2021)
- [Risk-Averse No-Regret Learning in Online Convex Games](https://mlsanity.com/paper/2203.08957/) (2022)
- [A Model-Based Method for Minimizing CVaR and Beyond](https://mlsanity.com/paper/2305.17498/) (2023)
- [A Survey of Learning Criteria Going Beyond the Usual Risk](https://mlsanity.com/paper/2110.04996/) (2021)
- [Revisiting adversarial training for the worst-performing class](https://mlsanity.com/paper/2302.08872/) (2023)
- [Flexible risk design using bi-directional dispersion](https://mlsanity.com/paper/2203.14434/) (2022)
- [A Zeroth-Order Momentum Method for Risk-Averse Online Convex Games](https://mlsanity.com/paper/2209.02838/) (2022)
- [Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization](https://mlsanity.com/paper/2404.01200/) (2024)
- [Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks](https://mlsanity.com/paper/2104.02373/) (2021)
- [Efficient Online-Bandit Strategies for Minimax Learning Problems](https://mlsanity.com/paper/2105.13939/) (2021)
- [Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity](https://mlsanity.com/paper/2208.03066/) (2022)
- [OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation](https://mlsanity.com/paper/2606.06096/) (2026)
- [Safe Collaborative Filtering](https://mlsanity.com/paper/2306.05292/) (2023)
- [ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining](https://mlsanity.com/paper/2505.19893/) (2025)
- [PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures](https://mlsanity.com/paper/2510.11169/) (2025)

## Abstract (arXiv)

In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples. To address this, we consider the problem of training models in a risk-averse manner. We propose an adaptive sampling algorithm for stochastically optimizing the Conditional Value-at-Risk (CVaR) of a loss distribution, which measures its performance on the α fraction of most difficult examples. We use a distributionally robust formulation of the CVaR to phrase the problem as a zero-sum game between two players, and solve it efficiently using regret minimization. Our approach relies on sampling from structured Determinantal Point Processes (DPPs), which enables scaling it to large data sets. Finally, we empirically demonstrate its effectiveness on large-scale convex and non-convex learning tasks.