Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models

• URL: http://arxiv.org/abs/2607.04360v1
• Date: Sun, 05 Jul 2026 15:38:35 GMT
• Title: Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models
• Abstract summary: Conditional generative models have emerged as powerful tools for sampling from target conditional distributions.<n>As these models proliferate, practitioners often face multiple plausible generators whose performance can vary with the task, data, or input condition.<n>We propose an optimal model averaging framework for conditional generative models, allowing candidate generators to be combined even when they are accessible only through conditional samples.
• Score: 5.102380962405881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conditional generative models have emerged as powerful tools for sampling from target conditional distributions, driving substantial advances across a wide range of scientific and applied domains. As these models proliferate, practitioners often face multiple plausible generators whose performance can vary with the task, data, or input condition. We propose an optimal model averaging framework for conditional generative models, allowing candidate generators to be combined even when they are accessible only through conditional samples without tractable densities. Specifically, we use a sample-based maximum mean discrepancy between conditional distributions, which first leads to a static model averaging method, StaticMA, assigning fixed weights to different candidates. In addition, we develop MoEMA (mixture-of-experts model averaging), an input-adaptive method that parameterizes covariate-dependent weights through a softmax neural-network gate. We establish in-sample and out-of-sample asymptotic optimality for the proposed methods, together with consistency of the estimated adaptive weight function under regularity conditions. The framework applies directly to Euclidean responses and extends to unstructured data by combining our formulation with fixed representation maps. Across a broad set of simulations and real-data studies spanning tabular, image, and text modalities, MoEMA generally improves over competing baselines, demonstrating the effectiveness of our proposed methods.

Related papers

• Variance-Reduced Model Predictive Path Integral via Quadratic Model Approximation [18.217598791860684]
  We introduce a hybrid variance-reduced MPPI framework that integrates a prior model into the sampling process.<n>We demonstrate that adopting a quadratic approximation enables the derivation of a closed-form, model-guided prior that effectively concentrates samples in informative regions.
  arXiv  Detail & Related papers  (2026-02-03T15:23:17Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Composition and Alignment of Diffusion Models using Constrained Learning [79.36736636241564]
  Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions.<n>Two commonly used methods are: (i) alignment, which involves fine-tuning a diffusion model to align it with a reward; and (ii) composition, which combines several pre-trained diffusion models, each emphasizing a desirable attribute in the generated outputs.<n>We propose a constrained optimization framework that unifies alignment and composition of diffusion models by enforcing that the aligned model satisfies reward constraints and/or remains close to (potentially multiple) pre-trained models.
  arXiv  Detail & Related papers  (2025-08-26T15:06:30Z)
• Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts [64.34482582690927]
  We provide an efficient and principled method for sampling from a sequence of annealed, geometric-averaged, or product distributions derived from pretrained score-based models.<n>We propose Sequential Monte Carlo (SMC) resampling algorithms that leverage inference-time scaling to improve sampling quality.
  arXiv  Detail & Related papers  (2025-03-04T17:46:51Z)
• Bridging the inference gap in Mutimodal Variational Autoencoders [6.246098300155483]
  Multimodal Variational Autoencoders offer versatile and scalable methods for generating unobserved modalities from observed ones.<n>Recent models using mixturesof-experts aggregation suffer from theoretically grounded limitations that restrict their generation quality on complex datasets.<n>We propose a novel interpretable model able to learn both joint and conditional distributions without introducing mixture aggregation.
  arXiv  Detail & Related papers  (2025-02-06T10:43:55Z)
• On the Laplace Approximation as Model Selection Criterion for Gaussian Processes [6.990493129893112]
  We introduce multiple metrics based on the Laplace approximation. Experiments show that our metrics are comparable in quality to the gold standard dynamic nested sampling.
  arXiv  Detail & Related papers  (2024-03-14T09:28:28Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• Control as Hybrid Inference [62.997667081978825]
  We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
  arXiv  Detail & Related papers  (2020-07-11T19:44:09Z)

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.