Distributionally robust risk evaluation with an isotonic constraint
Not on the map. Why?
Abstract (arXiv)
Statistical learning under distribution shift is challenging when neither prior knowledge nor fully accessible data from the target distribution is available. Distributionally robust learning (DRL) aims to control the worst-case statistical performance within an uncertainty set of candidate distributions, but how to properly specify the set remains challenging. To enable distributional robustness without being overly conservative, in this paper, we propose a shape-constrained approach to DRL, which incorporates prior information about the way in which the unknown target distribution differs from its estimate. More specifically, we assume the unknown density ratio between the target distribution and its estimate is isotonic with respect to some partial order. At the population level, we provide a solution to the shape-constrained optimization problem that does not involve the isotonic constraint. At the sample level, we provide consistency results for an empirical estimator of the target in a range of different settings. Empirical studies on both synthetic and real data examples demonstrate the improved accuracy of the proposed shape-constrained approach.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 47 of its 116 references that are in the map. First posted on arXiv 9 Jul 2024.
Builds on
47 of 116 references.
References · 47
- 2016Distribution-Free Predictive Inference For Regressioncited by 657
- 2019Conformal Prediction Under Covariate Shiftcited by 511
- 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
- 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
- 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 182
- 2016Variance-based regularization with convex objectivescited by 153
- 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 150
- 2015Distributionally Robust Logistic Regressioncited by 124
- 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
- 2020Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimalitycited by 89
- 2019Support and Invertibility in Domain-Invariant Representationscited by 87
- 2020Robust Validation: Confident Predictions Even When Distributions Shiftcited by 82
35 more
- 2021Transfer Learning under High-dimensional Generalized Linear Modelscited by 69
- 2019Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifiercited by 64
- 2020On the Value of Target Data in Transfer Learningcited by 62
- 2021Sensitivity Analysis of Individual Treatment Effects: A Robust Conformal Inference Approachcited by 62
- 2021Conformalized Survival Analysiscited by 53
- 2022Optimally tackling covariate shift in RKHS-based nonparametric regressioncited by 53
- 2022Doubly Robust Calibration of Prediction Sets under Covariate Shiftcited by 40
- 2018Bounds on the conditional and average treatment effect with unobserved confounding factorscited by 39
- 2014SLOPE - Adaptive variable selection via convex optimizationcited by 33
- 2017Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrapcited by 33
- 2022A new similarity measure for covariate shift with applications to nonparametric regressioncited by 33
- 2019Isotonic Distributional Regressioncited by 28
- 2022Prediction Sets Adaptive to Unknown Covariate Shiftcited by 22
- 2023Classifier Calibration with ROC-Regularized Isotonic Regressioncited by 19
- 2022Conformalized survival analysis with adaptive cutoffscited by 17
- 2023Causal isotonic calibration for heterogeneous treatment effectscited by 16
- 2024Not all distributional shifts are equal: Fine-grained robust conformal inferencecited by 15
- 2023Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shiftcited by 14
- 2023Conformalized matrix completioncited by 13
- 2022Sensitivity analysis under the f-sensitivity models: a distributional robustness perspectivecited by 12
- 2022Learning from a Biased Samplecited by 12
- 2021The s-value: evaluating stability with respect to distributional shiftscited by 10
- 2023Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shiftscited by 9
- 2021Covariate Balancing Sensitivity Analysis for Extrapolating Randomized Trials across Locationscited by 8
- 2023Hidden yet quantifiable: A lower bound for confounding strength using randomized trialscited by 8
- 2023Statistical Limit Theorems in Distributionally Robust Optimizationcited by 7
- 2024De-Biased Two-Sample U-Statistics With Application To Conditional Distribution Testingcited by 6
- 2023Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implicationscited by 5
- 2022Variance-based sensitivity analysis for weighting estimators result in more informative boundscited by 4
- 2022Minimax Optimal Estimation of Stability Under Distribution Shiftcited by 4
- 2023Distributionally Robust Learning for Multi-source Unsupervised Domain Adaptationcited by 4
- 2022Distributionally robust and generalizable inferencecited by 3
- 2024On the design-dependent suboptimality of the Lassocited by 3
- 2019Partition-based Distributionally Robust Optimization via Optimal Transport with Order Cone Constraintscited by 1
- 2023A Bilateral Bound on the Mean-Square Error for Estimation in Model Mismatchcited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.