Overfitting in Adaptive Robust Optimization

• URL: http://arxiv.org/abs/2509.16451v2
• Date: Wed, 22 Oct 2025 20:35:40 GMT
• Title: Overfitting in Adaptive Robust Optimization
• Authors: Karl Zhu, Dimitris Bertsimas,
• Abstract summary: We propose assigning constraint-specific uncertainty set sizes, with harder constraints given stronger probabilistic guarantees.<n>This view motivates a principled approach to designing uncertainty sets that balances robustness and adaptivity.
• Score: 4.66948282422762
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adaptive robust optimization (ARO) extends static robust optimization by allowing decisions to depend on the realized uncertainty - weakly dominating static solutions within the modeled uncertainty set. However, ARO makes previous constraints that were independent of uncertainty now dependent, making it vulnerable to additional infeasibilities when realizations fall outside the uncertainty set. This phenomenon of adaptive policies being brittle is analogous to overfitting in machine learning. To mitigate against this, we propose assigning constraint-specific uncertainty set sizes, with harder constraints given stronger probabilistic guarantees. Interpreted through the overfitting lens, this acts as regularization: tighter guarantees shrink adaptive coefficients to ensure stability, while looser ones preserve useful flexibility. This view motivates a principled approach to designing uncertainty sets that balances robustness and adaptivity.

Related papers

• Uncertainty-aware Generative Recommendation [52.0751022792023]
  Uncertainty-aware Generative Recommendation (UGR) is a unified framework that leverages uncertainty as a critical signal for adaptive optimization.<n>UGR not only yields superior recommendation performance but also fundamentally stabilizes training, preventing the performance degradation often observed in standard methods.
  arXiv  Detail & Related papers  (2026-02-12T08:48:51Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• When Robustness Meets Conservativeness: Conformalized Uncertainty Calibration for Balanced Decision Making [8.234618636958462]
  We propose a new framework that provides distribution-free, finite-sample guarantees on miscoverage and regret.<n>Our method constructs valid estimators that trace out the mis-regret frontier.<n>These results offer the first principled data-driven methodology for guiding robustness selection.
  arXiv  Detail & Related papers  (2025-10-09T03:38:17Z)
• Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality [53.525547349715595]
  We propose a novel primal-only algorithm called Rectified Robust Policy Optimization (RRPO)<n>RRPO operates directly on the primal problem without relying on dual formulations.<n>We show convergence to an approximately optimal feasible policy with complexity matching the best-known lower bound.
  arXiv  Detail & Related papers  (2025-08-24T16:59:38Z)
• Adaptive Conformal Inference by Betting [51.272991377903274]
  We consider the problem of adaptive conformal inference without any assumptions about the data generating process.<n>Existing approaches for adaptive conformal inference are based on optimizing the pinball loss using variants of online gradient descent.<n>We propose a different approach for adaptive conformal inference that leverages parameter-free online convex optimization techniques.
  arXiv  Detail & Related papers  (2024-12-26T18:42:08Z)
• End-to-End Conformal Calibration for Optimization Under Uncertainty [32.844953018302874]
  This paper develops an end-to-end framework to learn the uncertainty estimates for conditional optimization. In addition, we propose to represent arbitrary convex uncertainty sets with partially convex neural networks. Our approach consistently improves upon two-stage-then-optimize.
  arXiv  Detail & Related papers  (2024-09-30T17:38:27Z)
• A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization [3.124884279860061]
  We introduce AGRO, a solution algorithm that performs adversarial generation for two-stage adaptive robust optimization.<n>AGRO generates high-dimensional contingencies that are simultaneously adversarial and realistic.<n>We show that AGRO outperforms the standard column-and-constraint algorithm by up to 1.8% in production-distribution planning and up to 11.6% in power system expansion.
  arXiv  Detail & Related papers  (2024-09-05T17:42:19Z)
• Resilient Constrained Reinforcement Learning [87.4374430686956]
  We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before study. It is challenging to identify appropriate constraint specifications due to the undefined trade-off between the reward training objective and the constraint satisfaction. We propose a new constrained RL approach that searches for policy and constraint specifications together.
  arXiv  Detail & Related papers  (2023-12-28T18:28:23Z)
• Robust Constrained Reinforcement Learning [21.316736188238806]
  Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. We propose a framework of robust constrained reinforcement learning under model uncertainty. The goal is to guarantee that constraints on utilities/costs are satisfied for all MDPs in the uncertainty set, and to maximize the worst-case reward performance over the uncertainty set.
  arXiv  Detail & Related papers  (2022-09-14T18:29:02Z)
• Distributional Robustness and Regularization in Reinforcement Learning [62.23012916708608]
  We introduce a new regularizer for empirical value functions and show that it lower bounds the Wasserstein distributionally robust value function. It suggests using regularization as a practical tool for dealing with $textitexternal uncertainty$ in reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-05T19:56:23Z)

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.