AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Denoising Implicit Variational Inference

Zitong Wang, Zekun Wu, Longlin Yu, Cheng Zhang

NeurIPS 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Variational inference theory and gradients · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a denoising-based approach to semi-implicit variational inference that addresses the intractable marginal score in ELBO optimization; full text unavailable, so details are limited to the abstract.

Problem

Optimizing the ELBO for semi-implicit variational inference is hard because the marginal score of the semi-implicit distribution is intractable, which existing UIVI-style reparameterized gradient estimators handle imperfectly.

Approach

Frames the intractable marginal score estimation in SIVI as a denoising problem, extending UIVI and related reparameterized ELBO gradient methods; specific mechanism not stated in the abstract provided.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace UIVI reverse-conditional MCMC with a score network trained by denoising score matchingsemi-implicit VI · Conditioned diffusion (100-dim)expected log marginal likelihood: 21.866 -> 75.162Improved
replace UIVI reverse-conditional MCMC with learned scoresemi-implicit VI · Conditioned diffusion (100-dim)wall-clock time (s): 756 -> 335Improved
replace UIVI with DIVI on BNN regressionsemi-implicit VI · BNN Proteintest RMSE: 5.021 -> 4.493Improved
replace UIVI with DIVI on BNN regressionsemi-implicit VI · BNN Bostontest RMSE: 3.266 -> 2.677Improved
use DIVI instead of KSIVI on BNN regressionsemi-implicit VI · BNN Wine Red and Yachttest RMSE: Yacht 1.274 (KSIVI) vs 1.358Mixed
replace UIVI with DIVI on BNN regression (cost)semi-implicit VI · BNN (six UCI datasets)avg wall-clock time (s): 842 -> 264Improved
use DIVI learned score instead of UIVI HMC score estimator (ablation)fixed DIVI variational checkpoints · X-shaped target, 10,000 stepssquared L2 score error: 899.236 -> 0.331Improved
use DIVI learned score instead of AISIVI importance-sampling score estimator (ablation)fixed DIVI variational checkpoints · X-shaped target, 10,000 stepssquared L2 score error: 6.881 -> 0.331Improved
use DIVI learned score instead of UIVI HMC estimator (ablation)score evaluation · X-shaped targetscore-evaluation time (ms): 204.523 -> 0.134Improved
use DIVI on two-dimensional targetssemi-implicit VI · 2D toy targets (x_shaped, student_uc, 8_gaussians)KL-style and Wasserstein metricsImproved

Limitations

Experimental setup

Baselines: Unbiased Implicit Variational Inference

Builds on: Unbiased Implicit Variational Inference Semi-implicit variational inference

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy