Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning

• URL: http://arxiv.org/abs/2605.25210v1
• Date: Sun, 24 May 2026 18:19:40 GMT
• Title: Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
• Abstract summary: We develop a principled MOL framework for diffusion models with limited data.<n>We propose a two-stage training procedure that first fits lightweight specialist models from limited paired data.<n>We establish bounds generalization showing that the required number of paired samples only depends on the complexity of the specialist model classes.
• Score: 83.65494573724904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance [9.797319790710711]
  We propose a multimodal deep generative model for semi-supervised learning under class imbalance.<n>Our approach uses separate encoders for each modality, sharing latent variables across modalities, and simplifies joint posterior computation with a product-of-experts method.<n>We derive a new objective function for training the proposed model on both labeled and unlabeled data using $$-power divergence.
  arXiv  Detail & Related papers  (2026-05-07T13:56:45Z)
• A theory of learning data statistics in diffusion models, from easy to hard [11.841482748098327]
  We show that diffusion models trained on natural images exhibit a distributional simplicity bias, learning simple, pair-wise input statistics before specializing to higher-order correlations.<n>We reproduce this behaviour in simple denoisers trained on a minimal data model, the mixed cumulant model.<n>Our work describes a key mechanism for how diffusion models can learn distributions of increasing complexity.
  arXiv  Detail & Related papers  (2026-03-13T11:07:01Z)
• Deep Multivariate Models with Parametric Conditionals [47.20275199636936]
  We consider deep multivariate models for heterogeneous collections of random variables.<n>We propose to represent the joint probability distribution by means of conditional probability distributions for each group of variables conditioned on the rest.<n>Their learning can be approached as training a parametrised Markov chain kernel by maximising the data likelihood of its limiting distribution.
  arXiv  Detail & Related papers  (2026-02-02T11:01:48Z)
• A Theory for Conditional Generative Modeling on Multiple Data Sources [20.539424639329564]
  This paper takes the first step toward a rigorous analysis of multi-source training in conditional generative modeling.<n>Our result shows that when source distributions share certain similarities and the model is expressive enough, multi-source training guarantees a sharper bound than single-source training.
  arXiv  Detail & Related papers  (2025-02-20T14:13:24Z)
• Constrained Diffusion Models via Dual Training [80.03953599062365]
  Diffusion processes are prone to generating samples that reflect biases in a training dataset. We develop constrained diffusion models by imposing diffusion constraints based on desired distributions. We show that our constrained diffusion models generate new data from a mixture data distribution that achieves the optimal trade-off among objective and constraints.
  arXiv  Detail & Related papers  (2024-08-27T14:25:42Z)
• Distributional Successor Features Enable Zero-Shot Policy Optimization [36.53356539916603]
  This work proposes a novel class of models, i.e., Distributional Successor Features for Zero-Shot Policy Optimization (DiSPOs)<n>DiSPOs learn a distribution of successor features of a stationary dataset's behavior policy, along with a policy that acts to realize different successor features achievable within the dataset.<n>By directly modeling long-term outcomes in the dataset, DiSPOs avoid compounding error while enabling a simple scheme for zero-shot policy optimization across reward functions.
  arXiv  Detail & Related papers  (2024-03-10T22:27:21Z)
• Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
  We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
  arXiv  Detail & Related papers  (2024-02-09T07:18:06Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Autoregressive Diffusion Models [34.125045462636386]
  We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and generalizing order-agnostic autoregressive models. ARDMs are simple to implement and easy to train, and can be trained using an efficient objective similar to modern probabilistic diffusion models. We show that ARDMs obtain compelling results not only on complete datasets, but also on compressing single data points.
  arXiv  Detail & Related papers  (2021-10-05T13:36:55Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.