[2603.04000] On the Learnability of Offline Model-Based Optimization: A Ranking Perspective

Computer Science > Machine Learning arXiv:2603.04000 (cs) [Submitted on 4 Mar 2026] Title:On the Learnability of Offline Model-Based Optimization: A Ranking Perspective Authors:Shen-Huan Lyu, Rong-Xi Tan, Ke Xue, Yi-Xiao He, Yu Huang, Qingfu Zhang, Chao Qian View a PDF of the paper titled On the Learnability of Offline Model-Based Optimization: A Ranking Perspective, by Shen-Huan Lyu and 6 other authors View PDF HTML (experimental) Abstract:Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good predictive accuracy leads to good optimization performance. In this work, we challenge this assumption and study offline MBO from a learnability perspective. We argue that offline optimization is fundamentally a problem of ranking high-quality designs rather than accurate value prediction. Specifically, we introduce an optimization-oriented risk based on ranking between near-optimal and suboptimal designs, and develop a unified theoretical framework that connects surrogate learning to final optimization. We prove the theoretical advantages of ranking over regression, and identify distributional mismatch between the training data and near-optimal designs as the dominant error. Inspired by this, we design a distribution-aware ranking method to reduce this mismatch. Empirical results across various tasks show t...