paper-with-me

Papers

A Contrastive Divergence for Combining Variational Inference and MCMC

2019-05-10 · Francisco J. R. Ruiz, Michalis K. Titsias

We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To make inference tractable, we introduce the variational contrastive divergence (VCD), a new divergence that replaces the standard Kullback-Leibler (KL) divergence used in VI. The VCD captures a notion of discrepancy between the initial variational distribution and its improved version (obtained after running the MCMC steps), and it converges asymptotically to the symmetrized KL divergence between the variational distribution and the posterior of interest. The VCD objective can be optimized efficiently with respect to the variational parameters via stochastic optimization. We show experimentally that optimizing the VCD leads to better predictive performance on two latent variable models: logistic matrix factorization and variational autoencoders (VAEs).

📄 PDF Abstract BibTeX arXiv:1905.04062

Code (3)

franrruiz/vcd_divergence 공식 구현
soran-ghaderi/torchebm pytorch
suryabulusu/VCD

Tasks

Stochastic OptimizationVariational Inference

Similar Papers 제목 키워드 기반

A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI

2017-06-20 · ICML 2017 8 · Justin Domke

Two popular classes of methods for approximate inference are Markov chain Monte Carlo (MCMC) and variational inference. MCMC tends to be accurate if run for a long enough time, while variational inference tends to give b…

Variational Inference

Why (and When and How) Contrastive Divergence Works

2014-05-03 · Ian E Fellows

Contrastive divergence (CD) is a promising method of inference in high dimensional distributions with intractable normalizing constants, however, the theoretical foundations justifying its use are somewhat shaky. This do…

Bayesian Pseudo-Coresets via Contrastive Divergence

2023-03-20 · Piyush Tiwary, Kumar Shubham, Vivek V. Kashyap, Prathosh A. P

Bayesian methods provide an elegant framework for estimating parameter posteriors and quantification of uncertainty associated with probabilistic models. However, they often suffer from slow inference times. To address t…

Dataset Condensation

Variational Inference for Neyman-Scott Processes

2023-03-07 · Chengkuan Hong, Christian R. Shelton

Neyman-Scott processes (NSPs) have been applied across a range of fields to model points or temporal events with a hierarchy of clusters. Markov chain Monte Carlo (MCMC) is typically used for posterior sampling in the mo…

Point ProcessesVariational Inference

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