The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization

2026-02-11 · Stephanie Holly, Alexandru-Ciprian Zăvoianu, Siegfried Silber, Sepp Hochreiter, Werner Zellinger arxiv

Offline multi-objective optimization (MOO) aims to recover Pareto-optimal designs given a finite, static dataset. Recent generative approaches, including diffusion models, show strong performance under hypervolume, yet their behavior under other established MOO metrics is less understood. We show that generative methods systematically underperform evolutionary alternatives with respect to other metrics, such as generational distance. We relate this failure mode to the offline-frontier shift, i.e., the displacement of the offline dataset from the Pareto front, which acts as a fundamental limitation in offline MOO. We argue that overcoming this limitation requires out-of-distribution sampling in objective space (via an integral probability metric) and empirically observe that generative methods remain conservatively close to the offline objective distribution. Our results position offline MOO as a distribution-shift--limited problem and provide a diagnostic lens for understanding when and why generative optimization methods fail.

📄 PDF Abstract BibTeX arXiv:2602.11126

Code (0)

등록된 구현이 없습니다.

Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage

2023-10-27 · Kishan Panaganti, Zaiyan Xu, Dileep Kalathil, Mohammad Ghavamzadeh

The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration. One of the main challenges in offline RL…

Offline RL Reinforcement Learning (RL)

Data-Driven Offline Decision-Making via Invariant Representation Learning

2022-11-21 · Han Qi, Yi Su, Aviral Kumar, Sergey Levine

The goal in offline data-driven decision-making is synthesize decisions that optimize a black-box utility function, using a previously-collected static dataset, with no active interaction. These problems appear in many f…

Decision Making Domain Adaptation Reinforcement Learning (RL)Representation Learning

Boosting Offline Reinforcement Learning via Data Rebalancing

2022-10-17 · Yang Yue, Bingyi Kang, Xiao Ma, Zhongwen Xu 외

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicit…

D4RL Offline RL reinforcement-learning Reinforcement Learning+1

COOPO: Cyclic Offline-Online Policy Optimization Algorithm

2026-05-18 · Qisai Liu, Zhanhong Jiang, Joshua Russell Waite, Aditya Balu 외 arxiv

Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment interactions. The recent advent of hybrid …

Reinforcement Learning

Balance Equation-based Distributionally Robust Offline Imitation Learning

2025-11-11 · Rishabh Agrawal, Yusuf Alvi, Rahul Jain, Ashutosh Nayyar arxiv

Imitation Learning (IL) has proven highly effective for robotic and control tasks where manually designing reward functions or explicit controllers is infeasible. However, standard IL methods implicitly assume that the e…