# Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach

arXiv: https://arxiv.org/abs/1610.03425 · HTML: https://mlsanity.com/paper/1610.03425/

## Key facts

- Cited by 183 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2016.

## Built on by (most cited first, 30 of 183)

- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [Examining and Combating Spurious Features under Distribution Shift](https://mlsanity.com/paper/2106.07171/) (2021)
- [Mandoline: Model Evaluation under Distribution Shift](https://mlsanity.com/paper/2107.00643/) (2021)
- [AutoBalance: Optimized Loss Functions for Imbalanced Data](https://mlsanity.com/paper/2201.01212/) (2022)
- [Unsupervised Learning of Debiased Representations with Pseudo-Attributes](https://mlsanity.com/paper/2108.02943/) (2021)
- [Model Agnostic Sample Reweighting for Out-of-Distribution Learning](https://mlsanity.com/paper/2301.09819/) (2023)
- [Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations](https://mlsanity.com/paper/2107.00520/) (2021)
- [Sinkhorn Distributionally Robust Optimization](https://mlsanity.com/paper/2109.11926/) (2021)
- [Deeply-Debiased Off-Policy Interval Estimation](https://mlsanity.com/paper/2105.04646/) (2021)
- [A Unified Wasserstein Distributional Robustness Framework for Adversarial Training](https://mlsanity.com/paper/2202.13437/) (2022)
- [A Finite Sample Complexity Bound for Distributionally Robust Q-learning](https://mlsanity.com/paper/2302.13203/) (2023)
- [Regularized Policies are Reward Robust](https://mlsanity.com/paper/2101.07012/) (2021)
- [Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2209.06620/) (2022)
- [Minimax Regret Optimization for Robust Machine Learning under Distribution Shift](https://mlsanity.com/paper/2202.05436/) (2022)
- [Applied Causal Inference Powered by ML and AI](https://mlsanity.com/paper/2403.02467/) (2024)
- [Modeling the Second Player in Distributionally Robust Optimization](https://mlsanity.com/paper/2103.10282/) (2021)
- [On the Optimality of Batch Policy Optimization Algorithms](https://mlsanity.com/paper/2104.02293/) (2021)
- [Simple and near-optimal algorithms for hidden stratification and multi-group learning](https://mlsanity.com/paper/2112.12181/) (2021)
- [Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics](https://mlsanity.com/paper/2105.03863/) (2021)
- [Statistical Analysis of Wasserstein Distributionally Robust Estimators](https://mlsanity.com/paper/2108.02120/) (2021)
- [Measuring Generalization with Optimal Transport](https://mlsanity.com/paper/2106.03314/) (2021)
- [Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization](https://mlsanity.com/paper/2305.11965/) (2023)
- [MetaSets: Meta-Learning on Point Sets for Generalizable Representations](https://mlsanity.com/paper/2204.07311/) (2022)
- [Augmented balancing weights as linear regression](https://mlsanity.com/paper/2304.14545/) (2023)
- [Adaptive Preference Scaling for Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2406.02764/) (2024)
- [Distributionally Robust Multilingual Machine Translation](https://mlsanity.com/paper/2109.04020/) (2021)

## Abstract (arXiv)

We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically. We develop a generalized empirical likelihood framework---based on distributional uncertainty sets constructed from nonparametric f-divergence balls---for Hadamard differentiable functionals, and in particular, stochastic optimization problems. As consequences of this theory, we provide a principled method for choosing the size of distributional uncertainty regions to provide one- and two-sided confidence intervals that achieve exact coverage. We also give an asymptotic expansion for our distributionally robust formulation, showing how robustification regularizes problems by their variance. Finally, we show that optimizers of the distributionally robust formulations we study enjoy (essentially) the same consistency properties as those in classical sample average approximations. Our general approach applies to quickly mixing stationary sequences, including geometrically ergodic Harris recurrent Markov chains.