mlsanityData to 14 Oct 2026

Bootstrap Your Flow

arXiv 2111.11510 ↗First posted 22 Nov 2021cs.LG cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Normalizing flows are flexible, parameterized distributions that can be used to approximate expectations from intractable distributions via importance sampling. However, current flow-based approaches are limited on challenging targets where they either suffer from mode seeking behaviour or high variance in the training loss, or rely on samples from the target distribution, which may not be available. To address these challenges, we combine flows with annealed importance sampling (AIS), while using the α-divergence as our objective, in a novel training procedure, FAB (Flow AIS Bootstrap). Thereby, the flow and AIS improve each other in a bootstrapping manner. We demonstrate that FAB can be used to produce accurate approximations to complex target distributions, including Boltzmann distributions, in problems where previous flow-based methods fail.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 36 of its 59 references that are in the map. First posted on arXiv 22 Nov 2021.

Builds on

36 of 59 references.

References · 36

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2015Variational Inference with Normalizing Flowscited by 2,170
  3. 2016Density estimation using Real NVPcited by 2,042
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  5. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  6. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  7. 2019An Introduction to Variational Autoencoderscited by 1,000
  8. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  10. 2019Neural Spline Flowscited by 596
  11. 2015Weight Uncertainty in Neural Networkscited by 554
  12. 2018Invertible Residual Networkscited by 365
24 more
  1. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  2. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 262
  3. 2019Residual Flows for Invertible Generative Modelingcited by 257
  4. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  5. 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 209
  6. 2018Neural Autoregressive Flowscited by 208
  7. 2020Stochastic Normalizing Flowscited by 157
  8. 2018Neural Importance Samplingcited by 155
  9. 2019Unconstrained Monotonic Neural Networkscited by 92
  10. 2019NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transportcited by 74
  11. 2018Sylvester Normalizing Flows for Variational Inferencecited by 72
  12. 2020SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flowscited by 71
  13. 2019Block Neural Autoregressive Flowcited by 62
  14. 2021Smooth Normalizing Flowscited by 53
  15. 2017Generalizing Hamiltonian Monte Carlo with Neural Networkscited by 52
  16. 2021Densely connected normalizing flowscited by 49
  17. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  18. 2016On the Quantitative Analysis of Decoder-Based Generative Modelscited by 40
  19. 2020Invertible Generative Modeling using Linear Rational Splinescited by 40
  20. 2017A-NICE-MC: Adversarial Training for MCMCcited by 38
  21. 2019Cubic-Spline Flowscited by 35
  22. 2013High-Dimensional Probability Estimation with Deep Density Modelscited by 17
  23. 2019Learning Deep Generative Models with Annealed Importance Samplingcited by 8
  24. 2020Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chainscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 0; 2025: 0; 2026: 1.

5 papers.

  1. 2022Torsional Diffusion for Molecular Conformer Generationcited by 263
  2. 2022Flow Annealed Importance Sampling Bootstrapcited by 127
  3. 2023Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flowscited by 9
  4. 2026Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopescited by 2
  5. 2023Training Normalizing Flows with the Precision-Recall Divergencecited by 0