A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models

• URL: http://arxiv.org/abs/2608.08770v1
• Date: Sun, 09 Aug 2026 15:41:01 GMT
• Title: A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
• Abstract summary: We formulate inference-time distributional control as targeting a tilted measure under a mean-field framework.<n>We derive a weighted interacting particle scheme to target it in a principled manner.<n> Empirically, we verify that the procedure correctly targets the prescribed distribution in tractable low-dimensional settings.
• Score: 3.2299643462065286
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are typically defined on individual samples, for many applications it is desirable to steer according to distribution-level rewards, for example to calibrate with population-level information or to encourage diversity. In both cases, simply incorporating the reward gradient into the dynamics, while often effective, comes with few theoretical guarantees on the sampled distribution. For pointwise rewards, recent work has therefore sought to develop a principled framework for targeting a prescribed tilted distribution using particle reweighting. However, an analogous theoretically-grounded approach for distributional rewards is currently lacking. In this work, we formulate inference-time distributional control as targeting a tilted measure under a mean-field framework, and derive a weighted interacting particle scheme to target it in a principled manner. Our framework recovers pointwise-reward steering as a special case, while providing a theoretical foundation for existing batch-level steering methods. Empirically, we verify that the procedure correctly targets the prescribed distribution in tractable low-dimensional settings, and investigate its behaviour in higher-dimensional protein conformation tasks.

Related papers

• Towards More General Control of Diffusion Models Using Jeffrey Guidance [21.06046163920049]
  Jeffrey guidance is a principled framework that extends diffusion-model control to applications beyond what standard guidance can express.<n>We first demonstrate Jeffrey guidance by targeting a prescribed embedding distribution.<n>With Inception embeddings as the target, this leads to substantial reductions in FID on both CIFAR-10 and FFHQ.
  arXiv  Detail & Related papers  (2026-06-11T11:53:53Z)
• A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows [6.695501393837496]
  We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein flows.<n>For a broad class of standard f-divergence objectives, we show that the induced velocity gradient field admits the universal form $mathbfV(x)=w(r(x)),(x)$.<n>We extend the framework beyond the f-divergence family to the Log-Variance (LV) divergence, analyze how the reference distribution alters the resulting drift structure, and motivate a practical LV-inspired surrogate for data-free training
  arXiv  Detail & Related papers  (2026-05-18T03:32:22Z)
• Inference-Time Attribute Distribution Alignment for Unconditional Diffusion [54.28942858023809]
  We formalize the inference-time attribute distributional alignment problem for pretrained unconditional diffusion models.<n>To address this, we cast inference-time attribute distributional alignment as an optimal control problem over the reverse diffusion process.<n>We solve for the perturbations using an optimal-control-based algorithm to optimize a differentiable distribution-matching objective.
  arXiv  Detail & Related papers  (2026-05-08T09:02:47Z)
• Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement [51.54933696252104]
  We introduce Iterative Reward-Guided Refinement (IterRef), a novel test-time scaling method tailored to discrete diffusion.<n>We formalize this process within a Multiple-Try Metropolis framework, proving convergence to the reward-aligned distribution.<n>IterRef achieves striking gains under low compute budgets, far surpassing prior state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-04T02:33:23Z)
• Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage [16.94974733994214]
  prevailing methods often circumvent the lack of target data by optimizing reverse KL-based objectives.<n>We propose a principled approach for training diffusion-based samplers by directly targeting an objective analogous to the forward KL divergence.<n>Our approach consistently outperforms existing neural samplers across all distributional distance metrics.
  arXiv  Detail & Related papers  (2025-05-26T02:48:26Z)
• Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows [69.8873421870522]
  importance sampling is a rare event simulation technique used in Monte Carlo simulations.<n>We propose a method for more efficient sampling by updating the proposal distribution in the latent space of a normalizing flow.
  arXiv  Detail & Related papers  (2025-01-06T21:18:02Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Flow Away your Differences: Conditional Normalizing Flows as an Improvement to Reweighting [0.0]
  We present an alternative to reweighting techniques for modifying distributions to account for a desired change in an underlying conditional distribution. We employ conditional normalizing flows to learn the full conditional probability distribution. In our examples, this leads to a statistical precision up to three times greater than using reweighting techniques with identical sample sizes for the source and target distributions.
  arXiv  Detail & Related papers  (2023-04-28T16:33:50Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)

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.