paper-with-me

홈 › Papers

What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization

2025-05-27 · Omar Bennouna, Amine Bennouna, Saurabh Amin, Asuman Ozdaglar

We study the fundamental question of how informative a dataset is for solving a given decision-making task. In our setting, the dataset provides partial information about unknown parameters that influence task outcomes. Focusing on linear programs, we characterize when a dataset is sufficient to recover an optimal decision, given an uncertainty set on the cost vector. Our main contribution is a sharp geometric characterization that identifies the directions of the cost vector that matter for optimality, relative to the task constraints and uncertainty set. We further develop a practical algorithm that, for a given task, constructs a minimal or least-costly sufficient dataset. Our results reveal that small, well-chosen datasets can often fully determine optimal decisions -- offering a principled foundation for task-aware data selection.

📄 PDF Abstract BibTeX arXiv:2505.21692

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

An exact counterfactual-example-based approach to tree-ensemble models interpretability

2021-05-31 · Pierre Blanchart

Explaining the decisions of machine learning models is becoming a necessity in many areas where trust in ML models decision is key to their accreditation/adoption. The ability to explain models decisions also allows to p…

counterfactualCounterfactual ExplanationFault DetectionFault localization+1

Optimizing Risk-averse Human-AI Hybrid Teams

2024-03-13 · Andrew Fuchs, Andrea Passarella, Marco Conti

We anticipate increased instances of humans and AI systems working together in what we refer to as a hybrid team. The increase in collaboration is expected as AI systems gain proficiency and their adoption becomes more w…

Exact Unlearning in Reinforcement Learning

2026-06-02 · Thanh Nguyen-Tang, Raman Arora arxiv

We formulate the problem of \emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon deletion request, i.e., the online learne…

Reinforcement Learning

A Machine Learning Approach to Two-Stage Adaptive Robust Optimization

2023-07-23 · Dimitris Bertsimas, Cheol Woo Kim

We propose an approach based on machine learning to solve two-stage linear adaptive robust optimization (ARO) problems with binary here-and-now variables and polyhedral uncertainty sets. We encode the optimal here-and-no…

HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling

2025-08-27 · Matthias Maiterth, Wesley H. Brewer, Jaya S. Kuruvella, Arunavo Dey 외 arxiv

Schedulers are critical for optimal resource utilization in high-performance computing. Traditional methods to evaluate schedulers are limited to post-deployment analysis, or simulators, which do not model associated inf…