mlsanityData to 7 Oct 2026

Nonparametric Automatic Differentiation Variational Inference with Spline Approximation

arXiv 2403.06302 ↗First posted 10 Mar 2024stat.ML cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Automatic Differentiation Variational Inference (ADVI) is efficient in learning probabilistic models. Classic ADVI relies on the parametric approach to approximate the posterior. In this paper, we develop a spline-based nonparametric approximation approach that enables flexible posterior approximation for distributions with complicated structures, such as skewness, multimodality, and bounded support. Compared with widely-used nonparametric variational inference methods, the proposed method is easy to implement and adaptive to various data structures. By adopting the spline approximation, we derive a lower bound of the importance weighted autoencoder and establish the asymptotic consistency. Experiments demonstrate the efficiency of the proposed method in approximating complex posterior distributions and improving the performance of generative models with incomplete data.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 72 references that are in the map. First posted on arXiv 10 Mar 2024.

Builds on

37 of 72 references.

References · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  7. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  8. 2016Deep Variational Information Bottleneckcited by 915
  9. 2019Neural Spline Flowscited by 590
  10. 2015Importance Weighted Autoencoderscited by 454
  11. 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
  12. 2017Advances in Variational Inferencecited by 236
25 more
  1. 2016Automatic Differentiation Variational Inferencecited by 159
  2. 2020Stochastic Normalizing Flowscited by 156
  3. 2020Normalizing Flows on Tori and Spherescited by 117
  4. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  5. 2017Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inferencecited by 97
  6. 2019Concrete Autoencoders for Differentiable Feature Selection and Reconstructioncited by 90
  7. 2018Tighter Variational Bounds are Not Necessarily Bettercited by 76
  8. 2017Frequentist Consistency of Variational Bayescited by 60
  9. 2017Gradient Estimators for Implicit Modelscited by 58
  10. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  11. 2017Convergence Rates of Variational Posterior Distributionscited by 45
  12. 2018A Spectral Approach to Gradient Estimation for Implicit Distributionscited by 45
  13. 2013Density Estimation in Infinite Dimensional Exponential Familiescited by 41
  14. 2018Variational Implicit Processescited by 41
  15. 2018Variational Autoencoder with Implicit Optimal Priorscited by 33
  16. 2022ExSpliNet: An interpretable and expressive spline-based neural networkcited by 33
  17. 2020Nonparametric Score Estimatorscited by 22
  18. 2018Doubly Semi-Implicit Variational Inferencecited by 19
  19. 2020Automatic Differentiation Variational Inference with Mixturescited by 19
  20. 2021Function-space Inference with Sparse Implicit Processescited by 13
  21. 2015Variational Gaussian Copula Inferencecited by 12
  22. 2022Deep Variational Implicit Processescited by 8
  23. 2017Boosting Variational Inference: an Optimization Perspectivecited by 7
  24. 2019Deep Random Splines for Point Process Intensity Estimation of Neural Population Datacited by 7
  25. 2022Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical studycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025Fisher meets Feynman: score-based variational inference with a product of expertscited by 2
  2. 2024Variational and Explanatory Neural Networks for Encoding Cancer Profiles and Predicting Drug Responsescited by 0
  3. 2026Structured Nonparametric Variational Inference for Dependent Latent Modelingcited by 0