mlsanityData to 14 Oct 2026

Auto-Encoding Sequential Monte Carlo

arXiv 1705.10306 ↗First posted 29 May 2017stat.MLcited by 65

Not on the map. Why?

Abstract (arXiv)

We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in structured probabilistic models and the flexibility of deep neural networks to model complex conditional probability distributions. We develop additional theoretical insights and introduce a new training procedure which improves both model and proposal learning. We demonstrate that our approach provides a fast, easy-to-implement and scalable means for simultaneous model learning and proposal adaptation in deep generative models.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 21; 2022: 9; 2023: 13; 2024: 10; 2025: 5; 2026: 6.

65 papers.

Sort:

By area:

  1. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 178
  2. 2021Annealed Flow Transport Monte Carlocited by 90
  3. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  4. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  5. 2022A Variational Perspective on Generative Flow Networkscited by 39
  6. 2021Differentiable Annealed Importance Sampling and the Perils of Gradient Noisecited by 36
  7. 2021Auto-differentiable Ensemble Kalman Filterscited by 28
  8. 2023An overview of differentiable particle filters for data-adaptive sequential Bayesian inferencecited by 23
  9. 2022SIXO: Smoothing Inference with Twisted Objectivescited by 22
  10. 2021Structured World Belief for Reinforcement Learning in POMDPcited by 21
  11. 2021Improving Lossless Compression Rates via Monte Carlo Bits-Back Codingcited by 19
  12. 2021Online Variational Filtering and Parameter Learningcited by 19
38 more
  1. 2021Differentiable Particle Filtering without Modifying the Forward Passcited by 18
  2. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  3. 2023Efficient Training of Energy-Based Models Using Jarzynski Equalitycited by 15
  4. 2024Inferring stochastic low-rank recurrent neural networks from neural datacited by 15
  5. 2021Nested Variational Inferencecited by 14
  6. 2021Surrogate Likelihoods for Variational Annealed Importance Samplingcited by 14
  7. 2023Reduced-Order Autodifferentiable Ensemble Kalman Filterscited by 14
  8. 2022A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 12
  9. 2021Variational Combinatorial Sequential Monte Carlo Methods for Bayesian Phylogenetic Inferencecited by 11
  10. 2021On Incorporating Inductive Biases into VAEscited by 11
  11. 2021Learning to Assimilate in Chaotic Dynamical Systemscited by 10
  12. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
  13. 2024Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inferencecited by 7
  14. 2021Learning Proposals for Probabilistic Programs with Inference Combinatorscited by 6
  15. 2021Variational Marginal Particle Filterscited by 6
  16. 2023Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Frameworkcited by 6
  17. 2023Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systemscited by 5
  18. 2023Online Variational Sequential Monte Carlocited by 5
  19. 2023NAS-X: Neural Adaptive Smoothing via Twistingcited by 4
  20. 2021An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulationscited by 3
  21. 2022Uphill Roads to Variational Tightness: Monotonicity and Monte Carlo Objectivescited by 3
  22. 2022Particle-Based Score Estimation for State Space Model Learning in Autonomous Drivingcited by 3
  23. 2023U-Statistics for Importance-Weighted Variational Inferencecited by 3
  24. 2023Variational autoencoder with weighted samples for high-dimensional non-parametric adaptive importance samplingcited by 3
  25. 2025Twice Sequential Monte Carlo for Tree Searchcited by 3
  26. 2022De-Sequentialized Monte Carlo: a parallel-in-time particle smoothercited by 2
  27. 2023Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplerscited by 2
  28. 2023Reparameterized Variational Rejection Samplingcited by 2
  29. 2023Learning Differentiable Particle Filter on the Flycited by 2
  30. 2024Revisiting semi-supervised training objectives for differentiable particle filterscited by 2
  31. 2024Regime Learning for Differentiable Particle Filterscited by 2
  32. 2025Deep Variational Sequential Monte Carlo for High-Dimensional Observationscited by 2
  33. 2025DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Modelscited by 2
  34. 2025PyDPF: A Python Package for Differentiable Particle Filteringcited by 2
  35. 2021Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Seriescited by 1
  36. 2022Optimization of Annealed Importance Sampling Hyperparameterscited by 1
  37. 2022Multi-Task Dynamical Systemscited by 1
  38. 2023Massively Parallel Reweighted Wake-Sleepcited by 1

50 most cited of 65 All 65 (JSON)