Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization

TL;DR

This paper introduces Pareto-Conditioned Diffusion (PCD), a new offline multi-objective optimization framework that uses conditional sampling to effectively explore trade-offs and outperform existing methods.

Contribution

The paper presents PCD, a novel diffusion-based approach that conditions on desired trade-offs and employs reweighting and reference directions to improve offline MOO.

Findings

PCD achieves state-of-the-art performance on offline MOO benchmarks.

PCD demonstrates greater consistency across diverse tasks.

PCD effectively explores the Pareto front beyond training data.

Abstract

Multi-objective optimization (MOO) arises in many real-world applications where trade-offs between competing objectives must be carefully balanced. In the offline setting, where only a static dataset is available, the main challenge is generalizing beyond observed data. We introduce Pareto-Conditioned Diffusion (PCD), a novel framework that formulates offline MOO as a conditional sampling problem. By conditioning directly on desired trade-offs, PCD avoids the need for explicit surrogate models. To effectively explore the Pareto front, PCD employs a reweighting strategy that focuses on high-performing samples and a reference-direction mechanism to guide sampling towards novel, promising regions beyond the training data. Experiments on standard offline MOO benchmarks show that PCD achieves highly competitive performance and, importantly, demonstrates greater consistency across diverse tasks than existing offline MOO approaches.