Constrained Diffusion Models with Primal-Dual Inference

• URL: http://arxiv.org/abs/2606.17192v1
• Date: Mon, 15 Jun 2026 18:32:33 GMT
• Title: Constrained Diffusion Models with Primal-Dual Inference
• Abstract summary: We develop constrained diffusion models with primal-dual inference (PDI)<n>PDI infers the optimal primal distribution and its parametrizing dual variable.<n>We evaluate PDI on constrained sampling from a mixture of Gaussians, wireless resource allocation, and portfolio management.
• Score: 76.64466170898369
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper develops constrained diffusion models with primal-dual inference (PDI) to sample from optimal distributions of entropy-regularized optimization problems with \emph{average} constraints. We formalize constrained sampling in the Lagrangian dual domain, where the optimal distribution takes the form of a Gibbs distribution indexed by the optimal dual variable. Rather than estimating this dual multiplier before sampling and freezing it throughout generation, PDI jointly infers the optimal primal distribution and its parametrizing dual variable. Each reverse diffusion step denoises using the score field associated with the current multiplier and then updates the multiplier through dual ascent using the estimated constraint violation of the denoised samples. To enable this conditional score field, we train a single dual-conditioned score network over the family of Gibbs distributions induced by the dual variables encountered during inference. We prove that the time average of the dual variables generated along the inference trajectory converges to a neighborhood of the dual optimum and bound the effect of residual dual mismatch on the terminal distribution through schedule-dependent stability factors. We evaluate PDI on constrained sampling from a mixture of Gaussians, wireless resource allocation, and portfolio management.

Related papers

• Reinforcing Few-step Generators via Reward-Tilted Distribution Matching [34.875805803270524]
  We propose Reward-Tilted Distribution Matching Distillation (RTDMD)<n>We show that minimizing KL divergence to a reward-tilted teacher distribution naturally decomposes into a distribution matching term and a reward term.<n>Experiments on SD3, SD3.5, and FLUX.2 demonstrate that RTDMD establishes new state-of-the-art results across preference, aesthetic, and compositional metrics.
  arXiv  Detail & Related papers  (2026-05-25T17:59:21Z)
• Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algorithm and Theory [2.148615003900331]
  We present FM4PDE, a flow-matching generative framework that learns the joint distribution of PDE coefficients.<n>Experiments on static and time-dependent benchmark PDEs demonstrate competitive accuracy and faster inference than diffusion-based generative models.
  arXiv  Detail & Related papers  (2026-05-25T07:14:11Z)
• Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification [1.0742675209112622]
  We propose a variational Bayesian framework that directly targets the posterior-predictive distribution and jointly learns variational approximations of both the posterior and the corresponding predictive distribution.<n>The proposed method achieves more accurate predictive distributions than conventional two-stage variational inference, while substantially reducing the cost of online predictive inference.
  arXiv  Detail & Related papers  (2026-05-05T12:56:00Z)
• A Unified View of Drifting and Score-Based Models [92.51878018325031]
  We make our relationship to the score-matching principle behind diffusion models precise by showing that drifting admits a score-based formulation on kernel-smoothed distributions.<n>We derive an exact decomposition for general radial kernels, and for the Laplace kernel we prove rigorous error bounds showing that drifting remains an accurate proxy for score matching in low-temperature and high-dimensional regimes.
  arXiv  Detail & Related papers  (2026-03-08T07:41:36Z)
• Direct Distributional Optimization for Provable Alignment of Diffusion Models [39.048284342436666]
  We introduce a novel alignment method for diffusion models from distribution optimization perspectives.<n>We first formulate the problem as a generic regularized loss minimization over probability distributions.<n>We enable sampling from the learned distribution by approximating its score function via Doob's $h$-transform technique.
  arXiv  Detail & Related papers  (2025-02-05T07:35:15Z)
• 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)
• 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)
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [49.97755400231656]
  We show that a new accelerated DDPM sampler achieves accelerated performance for three broad distribution classes not considered before.<n>Our results show an improved dependency on the data dimension $d$ among accelerated DDPM type samplers.
  arXiv  Detail & Related papers  (2024-02-21T16:11:47Z)
• 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)
• Joint control variate for faster black-box variational inference [32.38477249925875]
  Black-box variational inference performance is sometimes hindered by the use of gradient estimators with high variance. This variance comes from two sources of randomness: Data subsampling and Monte Carlo sampling.
  arXiv  Detail & Related papers  (2022-10-13T18:36:20Z)
• Sinkhorn Distributionally Robust Optimization [18.46110328123008]
  Sinkhorn distance is a variant of Wasserstein distance based on entropic regularization.<n>We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions.
  arXiv  Detail & Related papers  (2021-09-24T12:40:48Z)
• Loss function based second-order Jensen inequality and its application to particle variational inference [112.58907653042317]
  Particle variational inference (PVI) uses an ensemble of models as an empirical approximation for the posterior distribution. PVI iteratively updates each model with a repulsion force to ensure the diversity of the optimized models. We derive a novel generalization error bound and show that it can be reduced by enhancing the diversity of models.
  arXiv  Detail & Related papers  (2021-06-09T12:13:51Z)

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.