Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918520813518848 |
|---|---|
| author | Cheng, Ziheng Huang, Yixiao Zhu, Hanlin Geng, Haoran Sojoudi, Somayeh Malik, Jitendra Abbeel, Pieter Guo, Xin |
| author_facet | Cheng, Ziheng Huang, Yixiao Zhu, Hanlin Geng, Haoran Sojoudi, Somayeh Malik, Jitendra Abbeel, Pieter Guo, Xin |
| contents | Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple environments in robotics with diffusion policies. This naturally leads to a multi-objective learning (MOL) problem. A key challenge is that achieving good Pareto trade-offs can require a generalist model class with substantially larger capacity than what suffices for solving any individual task, thereby increasing statistical cost since sample complexity typically scales with the model complexity. To reconcile this, we develop a principled MOL framework for diffusion models with limited data: a semi-supervised regime where paired (labeled) samples are scarce, but (unlabeled) condition data are abundant. We propose a two-stage training procedure that first fits lightweight specialist models from limited paired data, and then distills them into a generalist model by generating pseudo-samples. We establish generalization bounds showing that the required number of paired samples only depends on the complexity of the specialist model classes. We further extend the theory to diffusion policies for sequential decision making to account for distribution shift in on-policy rollouts. Extensive experiments on robotic control and image restoration tasks are conducted to verify our theoretical results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25210 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning Cheng, Ziheng Huang, Yixiao Zhu, Hanlin Geng, Haoran Sojoudi, Somayeh Malik, Jitendra Abbeel, Pieter Guo, Xin Machine Learning Artificial Intelligence Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple environments in robotics with diffusion policies. This naturally leads to a multi-objective learning (MOL) problem. A key challenge is that achieving good Pareto trade-offs can require a generalist model class with substantially larger capacity than what suffices for solving any individual task, thereby increasing statistical cost since sample complexity typically scales with the model complexity. To reconcile this, we develop a principled MOL framework for diffusion models with limited data: a semi-supervised regime where paired (labeled) samples are scarce, but (unlabeled) condition data are abundant. We propose a two-stage training procedure that first fits lightweight specialist models from limited paired data, and then distills them into a generalist model by generating pseudo-samples. We establish generalization bounds showing that the required number of paired samples only depends on the complexity of the specialist model classes. We further extend the theory to diffusion policies for sequential decision making to account for distribution shift in on-policy rollouts. Extensive experiments on robotic control and image restoration tasks are conducted to verify our theoretical results. |
| title | Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.25210 |