6 papers · 1 filter
Learning Decision-Sufficient Representations for Linear Optimization
Yuhan Ye, Saurabh Amin, Asuman Ozdaglar
We study how to construct compressed datasets that suffice to recover optimal decisions in linear programs with an unknown cost vector lying in a prior set . Recen…
Data Informativeness in Linear Optimization under Uncertainty
Omar Bennouna, Amine Bennouna, Saurabh Amin +1
We study the problem of determining what data is required to solve a decision-making task when only partial information about the state of the world is available. Focusing on linea…
Zeroth-Order Constrained Optimization from a Control Perspective via Feedback Linearization
Runyu Zhang, Gioele Zardini, Asuman Ozdaglar +2
Safe derivative-free optimization under unknown constraints is a fundamental challenge in modern learning and control. Existing zeroth-order (ZO) methods typically still assume acc…
Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games
Fathima Zarin Faizal, Asuman Ozdaglar, Martin J. Wainwright
We study best-response type learning dynamics for zero-sum polymatrix games under two information settings. The two settings are distinguished by the type of information that each…
What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
Omar Bennouna, Amine Bennouna, Saurabh Amin +1
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 p…
Addressing misspecification in contextual optimization
Omar Bennouna, Jiawei Zhang, Saurabh Amin +1
We study a linear contextual optimization problem where a decision maker has access to historical data and contextual features to learn a cost prediction model aimed at minimizing…