paper-with-me

홈 › Papers

StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow

2026-05-15 · Gurjeet Jagwani, Stephen Thorp, Sinan Deger, Hiranya Peiris arxiv

Diffusion and flow-based models are ubiquitously used for generative modelling and density estimation. They admit a deterministic probability flow ordinary differential equation (PF-ODE), analogous to continuous normalizing flows (CNFs), which describes the transport of the probability mass. Obtaining the likelihood from these models is of interest to many workflows, especially Bayesian analysis, and requires solving the trace of the Jacobian to compute the divergence of the learned PF-ODE, which is either $\mathcal{O}(D^2)$ to compute exactly or $\mathcal{O}(D)$ with a noisy estimate. We introduce StAD, a new distillation method to predict and learn the divergence of the PF-ODE using the Langevin-Stein operator without ever computing the Jacobian. We show that our method is competitive with the Hutchinson and Hutch++ on CIFAR-10, ImageNet and other density estimation tasks, consistently improving the variance and speed of the likelihood predictions compared to the Hutchinson. We additionally show our method will generalize to a varied class of generative models, and show that under some regularity conditions these learned vector fields can be made to satisfy the Stein class.

📄 PDF Abstract BibTeX arXiv:2605.16486

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE

2017-07-04 · Qiang Liu, Dilin Wang

We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generati…

Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

2020-04-05 · Yuxuan Song, Qiwei Ye, Minkai Xu, Tie-Yan Liu

Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \textit{e.g.}, $f$-divergence~($f$-GANs) or In…

Image Generation

Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

2020-10-23 · Anonymous

Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \textit{e.g.}, $f$-divergence~($f$-GANs) or In…

Image Generation

Improving the Accuracy of Amortized Model Comparison with Self-Consistency

2025-08-28 · Šimon Kucharský, Aayush Mishra, Daniel Habermann, Stefan T. Radev 외 arxiv

Amortized Bayesian model comparison (BMC) enables fast probabilistic ranking of models via simulation-based training of neural surrogates. However, the accuracy of neural surrogates deteriorates when simulation models ar…

Stein Variational Gaussian Processes

2020-09-25 · Thomas Pinder, Christopher Nemeth, David Leslie

We show how to use Stein variational gradient descent (SVGD) to carry out inference in Gaussian process (GP) models with non-Gaussian likelihoods and large data volumes. Markov chain Monte Carlo (MCMC) is extremely compu…

Gaussian ProcessesVariational Inference