Denoising method improves sampling efficiency in variational inference

Denoising Implicit Variational Inference

Machine Learning

Summary

Variational inference is a technique to estimate complex probability distributions but can be slow and unstable when trying to improve accuracy. The authors propose a new method called Denoising Implicit Variational Inference (DIVI) that learns an important mathematical component directly, making the process more reliable and less costly. They tested DIVI on simulated and real-world data, showing it works better than previous methods. This method helps create better models for understanding uncertainty in data.

What this means in practice

  • For machine learning engineers: Accelerate training of variational models by replacing expensive sampling with a learned score network evaluation.
  • For bayesian data analysts: Improve accuracy and stability in Bayesian inference tasks using semi-implicit variational methods enhanced by denoising score matching.

Authors

Zitong Wang, Zekun Wu, Longlin Yu, Cheng Zhang

Abstract

Semi-implicit variational inference (SIVI) expands the representational capacity of variational families, but optimizing the Evidence Lower Bound (ELBO) remains challenging because the marginal score of the semi-implicit distribution is generally intractable. Unbiased Implicit Variational Inference (UIVI) and related methods address this difficulty through reparameterized ELBO gradients, but existing approaches estimate the required score indirectly through reverse-conditional sampling or approximation, which can be computationally costly and unstable. We propose Denoising Implicit Variational Inference (DIVI), which learns the marginal score directly via denoising score matching. The learned score is used as a plug-in estimator in the pathwise ELBO gradient, replacing inner reverse-conditional sampling with a score-network evaluation. We analyze DIVI as inexact stochastic gradient ascent and show, under stated assumptions, that the averaged stationarity measure is controlled by the usual optimization term and the average score-matching error. Empirically, we evaluate DIVI on both synthetic distributions and a variety of real-data Bayesian inference tasks. The results show that DIVI improves over the current UIVI baselines while reducing the cost of ELBO-gradient estimation.