Saved in:
Bibliographic Details
Main Authors: Shrestha, Jatan, Heiskanen, Santeri, Hepola, Kari, Rissanen, Severi, Jääskeläinen, Pekka, Pajarinen, Joni
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.00737
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908833032437760
author Shrestha, Jatan
Heiskanen, Santeri
Hepola, Kari
Rissanen, Severi
Jääskeläinen, Pekka
Pajarinen, Joni
author_facet Shrestha, Jatan
Heiskanen, Santeri
Hepola, Kari
Rissanen, Severi
Jääskeläinen, Pekka
Pajarinen, Joni
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00737
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
Shrestha, Jatan
Heiskanen, Santeri
Hepola, Kari
Rissanen, Severi
Jääskeläinen, Pekka
Pajarinen, Joni
Machine Learning
Artificial Intelligence
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.
title Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.00737