Learning Decision-Sufficient Representations for Linear Optimization

Yuhan Ye, Saurabh Amin, Asuman E. Ozdaglar

Abstract: We study how to construct compressed datasets that suffice to recover optimal decisions in linear programs with unknown cost vector $c$ lying in a prior set $\mathcal{C}$. Recent work by Bennouna et al. provides an exact geometric characterization of sufficient decision datasets (SDDs) via an intrinsic decision-relevant dimension $d^\star$. However, their algorithm for constructing minimum-size SDDs requires solving mixed-integer programs. In this paper, we establish hardness results: computing $d^\star$ is NP-hard and deciding whether a dataset is globally sufficient is coNP-hard, thereby resolving an open problem from their follow-up work on data informativeness in linear optimization. To circumvent worst-case intractability, we introduce pointwise sufficiency, a relaxation that requires sufficiency for an individual cost vector. We provide a polynomial-time cutting-plane algorithm to construct pointwise-sufficient decision datasets under nondegeneracy. In a data-driven regime with i.i.d. costs, we propose a cumulative algorithm that aggregates decision-relevant directions across samples, yielding a stable compression scheme of size at most $d^\star$. This leads to a distribution-free PAC guarantee: with high probability over the training sample, the pointwise sufficiency failure probability on a fresh draw is at most $\widetilde{O}(d^\star/n)$, and this rate is tight up to logarithmic factors. Finally, we apply decision-sufficient representations to contextual linear optimization, obtaining compressed predictors with generalization bounds scaling as $\widetilde{O}(\sqrt{d^\star/n})$ rather than $\widetilde{O}(\sqrt{d/n})$, where $d$ is the ambient cost dimension.