Distributionally robust risk evaluation with an isotonic constraint

• URL: http://arxiv.org/abs/2407.06867v3
• Date: Thu, 07 Nov 2024 14:09:12 GMT
• Title: Distributionally robust risk evaluation with an isotonic constraint
• Authors: Yu Gui, Rina Foygel Barber, Cong Ma,
• Abstract summary: Distributionally robust learning aims to control the worst-case statistical performance within an uncertainty set of candidate distributions. 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. Empirical studies on both synthetic and real data examples demonstrate the improved accuracy of the proposed shape-constrained approach.
• Score: 20.74502777102024
• License:
• Abstract: 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.

Related papers

• Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework [8.572441599469597]
  We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes. The objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected from unknown behavior policies. We show that our algorithm is sample-efficient, error-robust, and provably convergent even in non-linear function approximation settings.
  arXiv  Detail & Related papers  (2023-09-23T06:35:44Z)
• Statistical Inference Under Constrained Selection Bias [20.862583584531322]
  We propose a framework that enables statistical inference in the presence of selection bias. The output is high-probability bounds on the value of an estimand for the target distribution. We analyze the computational and statistical properties of methods to estimate these bounds and show that our method can produce informative bounds on a variety of simulated and semisynthetic tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:05:26Z)
• Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity [24.874664446700272]
  This paper studies a new framework that unifies the three approaches and that addresses the two challenges mentioned above. The properties (e.g., consistency and normalities), non-asymptotic properties (e.g., unbiasedness and error bound), and a Monte-Carlo-based solution method of the proposed model are studied.
  arXiv  Detail & Related papers  (2023-01-31T11:33:18Z)
• Uncertainty-guided Source-free Domain Adaptation [77.3844160723014]
  Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. We propose quantifying the uncertainty in the source model predictions and utilizing it to guide the target adaptation.
  arXiv  Detail & Related papers  (2022-08-16T08:03:30Z)
• Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity [39.886149789339335]
  offline reinforcement learning aims to learn to perform decision making from history data without active exploration. Due to uncertainties and variabilities of the environment, it is critical to learn a robust policy that performs well even when the deployed environment deviates from the nominal one used to collect the history dataset. We consider a distributionally robust formulation of offline RL, focusing on robust Markov decision processes with an uncertainty set specified by the Kullback-Leibler divergence in both finite-horizon and infinite-horizon settings.
  arXiv  Detail & Related papers  (2022-08-11T11:55:31Z)
• Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach [150.8920602230832]
  We propose a framework for learning calibrated uncertainties under domain shifts. In particular, the density ratio estimation reflects the closeness of a target (test) sample to the source (training) distribution. We show that our proposed method generates calibrated uncertainties that benefit downstream tasks.
  arXiv  Detail & Related papers  (2020-10-08T02:10:54Z)
• Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data [66.78671826743884]
  The distributionally robust optimization framework is considered for training a parametric model. The objective is to endow the trained model with robustness against adversarially manipulated input data. Proposed algorithms offer robustness with little overhead.
  arXiv  Detail & Related papers  (2020-07-07T18:25:25Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Nonparametric Estimation of Uncertainty Sets for Robust Optimization [2.741266294612776]
  We investigate a data-driven approach to constructing uncertainty sets for robust optimization problems. We provide a nonparametric method to estimate uncertainty sets whose probability mass is guaranteed to approximate a given target mass.
  arXiv  Detail & Related papers  (2020-04-07T01:47:55Z)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)
• Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning [70.01650994156797]
  Off- evaluation of sequential decision policies from observational data is necessary in batch reinforcement learning such as education healthcare. We develop an approach that estimates the bounds of a given policy. We prove convergence to the sharp bounds as we collect more confounded data.
  arXiv  Detail & Related papers  (2020-02-11T16:18:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.