mlsanityData to 14 Oct 2026

Semi-Implicit Variational Inference via Score Matching

arXiv 2308.10014 ↗First posted 19 Aug 2023stat.ML cs.LG stat.MEcited by 19

Not on the map. Why?

Abstract (arXiv)

Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational families by considering implicit variational distributions defined in a hierarchical manner. However, due to the intractable densities of variational distributions, current SIVI approaches often use surrogate evidence lower bounds (ELBOs) or employ expensive inner-loop MCMC runs for unbiased ELBOs for training. In this paper, we propose SIVI-SM, a new method for SIVI based on an alternative training objective via score matching. Leveraging the hierarchical structure of semi-implicit variational families, the score matching objective allows a minimax formulation where the intractable variational densities can be naturally handled with denoising score matching. We show that SIVI-SM closely matches the accuracy of MCMC and outperforms ELBO-based SIVI methods in a variety of Bayesian inference tasks.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 19 Aug 2023.

Builds on

29 of 52 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2015Variational Inference with Normalizing Flowscited by 2,170
  5. 2016Density estimation using Real NVPcited by 2,042
  6. 2016Variational Inference: A Review for Statisticianscited by 1,472
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  8. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  9. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  10. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
  11. 2013Black Box Variational Inferencecited by 319
  12. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
17 more
  1. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  2. 2015Measuring Sample Quality with Stein's Methodcited by 94
  3. 2017Gradient Estimators for Implicit Modelscited by 58
  4. 2018Semi-Implicit Variational Inferencecited by 55
  5. 2018A Spectral Approach to Gradient Estimation for Implicit Distributionscited by 45
  6. 2017Variational Inference using Implicit Distributionscited by 39
  7. 2018Deep Energy Estimator Networkscited by 34
  8. 2018Unbiased Implicit Variational Inferencecited by 33
  9. 2013Variational Relevance Vector Machinescited by 21
  10. 2018Stein Neural Samplercited by 19
  11. 2016Operator Variational Inferencecited by 16
  12. 2014Information Theoretical Estimators Toolboxcited by 15
  13. 2015Linear Response Methods for Accurate Covariance Estimates from Mean Field Variational Bayescited by 14
  14. 2016Variational Hamiltonian Monte Carlo via Score Matchingcited by 14
  15. 2019Variational approximations using Fisher divergencecited by 13
  16. 2021Efficient Semi-Implicit Variational Inferencecited by 9
  17. 2020Fisher Auto-Encoderscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 4; 2026: 5.

19 papers.

Sort:

By area:

  1. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  2. 2024Batch and match: black-box variational inference with a score-based divergencecited by 22
  3. 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Accelerationcited by 14
  4. 2024Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generationcited by 13
  5. 2025Few-Step Diffusion via Score identity Distillationcited by 12
  6. 2024EigenVI: score-based variational inference with orthogonal function expansionscited by 11
  7. 2024Kernel Semi-Implicit Variational Inferencecited by 8
  8. 2024Particle Semi-Implicit Variational Inferencecited by 7
  9. 2024On Divergence Measures for Training GFlowNetscited by 6
  10. 2023Wasserstein Gradient Flow over Variational Parameter Space for Variational Inferencecited by 5
  11. 2024Semi-Implicit Functional Gradient Flow for Efficient Samplingcited by 1
  12. 2026A Kernel Approach for Semi-implicit Variational Inferencecited by 1
7 more
  1. 2026Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networkscited by 1
  2. 2025Revisiting Unbiased Implicit Variational Inferencecited by 0
  3. 2025Semi-Implicit Variational Inference via Kernelized Path Gradient Descentcited by 0
  4. 2025Continuous Semi-Implicit Modelscited by 0
  5. 2026Large-scale empirical tuning and comparison of default optimizers for variational inferencecited by 0
  6. 2026Implicit Variational Rejection Samplingcited by 0
  7. 2026QuanVI: Score-based Variational Inference via Quantum Maximally Mixed Statescited by 0