Approximate sampling and estimation of partition functions using neural networks

2022-09-21 · George T. Cantwell

We consider the closely related problems of sampling from a distribution known up to a normalizing constant, and estimating said normalizing constant. We show how variational autoencoders (VAEs) can be applied to this task. In their standard applications, VAEs are trained to fit data drawn from an intractable distribution. We invert the logic and train the VAE to fit a simple and tractable distribution, on the assumption of a complex and intractable latent distribution, specified up to normalization. This procedure constructs approximations without the use of training data or Markov chain Monte Carlo sampling. We illustrate our method on three examples: the Ising model, graph clustering, and ranking.

📄 PDF Abstract BibTeX arXiv:2209.10423

Code (1)

gcant/distvae 공식 구현 tf

Tasks

ClusteringGraph Clustering

Partition Function Estimation under Bounded f-Divergence

2026-02-26 · Adam Block, Abhishek Shetty arxiv

We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio for a target distribution. While partition function estimation is a c…

An iterative step-function estimator for graphons

2014-12-05 · Diana Cai, Nathanael Ackerman, Cameron Freer

Exchangeable graphs arise via a sampling procedure from measurable functions known as graphons. A natural estimation problem is how well we can recover a graphon given a single graph sampled from it. One general framewor…

Clustering Graphon Estimation

Sampling from multimodal distributions with warm starts: Non-asymptotic bounds for the Reweighted Annealed Leap-Point Sampler

2025-12-19 · Holden Lee, Matheau Santana-Gijzen arxiv

Sampling from multimodal distributions is a central challenge in Bayesian inference and machine learning. In light of hardness results for sampling -- classical MCMC methods, even with tempering, can suffer from exponent…

Bayesian Inference

Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation

2023-03-06 · David Holzmüller, Francis Bach

Sampling from Gibbs distributions $p(x) \propto \exp(-V(x)/\varepsilon)$ and computing their log-partition function are fundamental tasks in statistics, machine learning, and statistical physics. However, while efficient…

Energy-Inspired Models: Learning with Sampler-Induced Distributions

2019-10-31 · NeurIPS 2019 12 · Dieterich Lawson, George Tucker, Bo Dai, Rajesh Ranganath

Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in EBMs relies on approximate sampling algor…

Variational Inference