Statistical Properties of Robust Learning under Distributional Shifts

• URL: http://arxiv.org/abs/2608.13133v1
• Date: Thu, 13 Aug 2026 12:06:48 GMT
• Title: Statistical Properties of Robust Learning under Distributional Shifts
• Abstract summary: This paper studies generalization error in the target environment---the excess loss under the shifted target distribution.<n>We derive finite-sample generalization error bounds in the shifted target environment for both DRO and RS.<n>We apply the framework to a network lot-sizing problem, using it to interpret how robust policies respond to positive shifts in the demand distribution.
• Score: 12.995907626827794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Distributional shifts arise when the target deployment environment differs from the source environment that generated the training data. Robust learning frameworks such as Distributionally Robust Optimization (DRO) and Robust Satisficing (RS) aim to address this challenge, yet their finite-sample guarantees under such shifts, and their systematic comparison, remain underexplored: existing analyses typically establish guarantees either in the source environment or for adversarial worst-case performance over an ambiguity set. This paper instead studies generalization error in the target environment---the excess loss under the shifted target distribution. Our contributions are threefold. First, we derive finite-sample generalization error bounds in the shifted target environment for both DRO and RS. These bounds explicitly characterize the trade-off between reduced sensitivity to shift and the regularization penalty induced by each method's robustness hyperparameter, and they avoid the curse of dimensionality associated with Wasserstein empirical concentration. Second, when partial shift information such as shift magnitude or direction is available, we propose information-directed hyperparameter calibrations and compare the two methods given the same information. Under these calibrations, and in the partial-information regimes we study, DRO and RS exhibit complementary theoretical and empirical behavior. Finally, we apply the framework to a network lot-sizing problem, using it to interpret how robust policies respond to positive shifts in the demand distribution. Together, these results fill a gap in understanding the statistical properties of robust learning methods under distributional shifts and provide a principled basis for comparing DRO and RS.

Related papers

• Disparate Impact in Synthetic Data Generation [10.23887083601828]
  We revisit the notion of disparate impact for synthetic data generation.<n>We argue that non-disparate impact is achieved when the synthetic and real distributions are the same.
  arXiv  Detail & Related papers  (2026-06-11T09:33:12Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents [90.45197506653341]
  Large language model (LLM) agents increasingly rely on external tools such as search engines to solve complex, multi-step problems.<n>The trajectories of search agents are structurally heterogeneous, where variations in the number, placement, and outcomes of search calls lead to fundamentally different answer directions and reward distributions.<n>Standard policy gradient methods, which use a single global baseline, suffer from what we identify and formalize as cross-stratum bias.<n>We propose Stratified GRPO, whose central component, Stratified Advantage Normalization (SAN), partitions trajectories into homogeneous strata based on their structural properties and computes advantages locally within each
  arXiv  Detail & Related papers  (2025-10-07T17:59:13Z)
• Distributionally Robust Federated Learning with Outlier Resilience [8.69285602685459]
  We study distributionally robust federated learning with explicit outlier resilience.<n>We reformulate the problem as a tractable Lagrangian penalty optimization, which admits robustness certificates.<n>Building on this reformulation, we propose the distributionally outlier-robust federated learning algorithm and establish its convergence guarantees.
  arXiv  Detail & Related papers  (2025-09-29T08:42:12Z)
• Distributionally Robust Optimization with Adversarial Data Contamination [49.89480853499918]
  We focus on optimizing Wasserstein-1 DRO objectives for generalized linear models with convex Lipschitz loss functions.<n>Our primary contribution lies in a novel modeling framework that integrates robustness against training data contamination with robustness against distributional shifts.<n>This work establishes the first rigorous guarantees, supported by efficient computation, for learning under the dual challenges of data contamination and distributional shifts.
  arXiv  Detail & Related papers  (2025-07-14T18:34:10Z)
• Knowledge Distillation and Enhanced Subdomain Adaptation Using Graph Convolutional Network for Resource-Constrained Bearing Fault Diagnosis [0.0]
  We propose a progressive knowledge distillation framework that transfers knowledge from a complex teacher model to a compact and efficient student model.<n>We introduce Enhanced Local Maximum Mean Squared Discrepancy (ELMMSD), which leverages mean and variance statistics in the Reproducing Kernel Hilbert Space (RKHS) and incorporates a priori probability distributions between labels.
  arXiv  Detail & Related papers  (2025-01-13T10:05:47Z)
• Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls [8.720733751119994]
  We study the underlying optimization problem, develop efficient solution algorithms, and demonstrate that the proposed method outperforms benchmark approaches on standard datasets.<n>Inspired by the former, we study the Wasserstein DR counterpart of ARO for logistic regression and show it admits a tractable convex optimization reformulation.
  arXiv  Detail & Related papers  (2024-07-18T15:59:37Z)
• Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits [18.982448033389588]
  Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. To account for the effect of different environments during learning and execution, distributionally robust optimization (DRO) methods have been developed. We propose a novel DRO approach that employs the Wasserstein distance instead.
  arXiv  Detail & Related papers  (2023-09-15T20:21:46Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• 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)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)

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.