mlsanityData to 14 Oct 2026

Filtering Variational Objectives

arXiv 1705.09279 ↗First posted 25 May 2017cs.LG cs.AI cs.NEcited by 91

Not on the map. Why?

Abstract (arXiv)

When used as a surrogate objective for maximum likelihood estimation in latent variable models, the evidence lower bound (ELBO) produces state-of-the-art results. Inspired by this, we consider the extension of the ELBO to a family of lower bounds defined by a particle filter's estimator of the marginal likelihood, the filtering variational objectives (FIVOs). FIVOs take the same arguments as the ELBO, but can exploit a model's sequential structure to form tighter bounds. We present results that relate the tightness of FIVO's bound to the variance of the particle filter's estimator by considering the generic case of bounds defined as log-transformed likelihood estimators. Experimentally, we show that training with FIVO results in substantial improvements over training the same model architecture with the ELBO on sequential data.

Key facts. Cited by 91 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 17; 2023: 19; 2024: 15; 2025: 5; 2026: 11.

91 papers.

Sort:

By area:

  1. 2023Score-based Data Assimilationcited by 96
  2. 2021Annealed Flow Transport Monte Carlocited by 90
  3. 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlocited by 90
  4. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  5. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  6. 2022A Variational Perspective on Generative Flow Networkscited by 39
  7. 2021Monte Carlo Variational Auto-Encoderscited by 36
  8. 2021Differentiable Annealed Importance Sampling and the Perils of Gradient Noisecited by 36
  9. 2021Auto-differentiable Ensemble Kalman Filterscited by 28
  10. 2023An overview of differentiable particle filters for data-adaptive sequential Bayesian inferencecited by 23
  11. 2022SIXO: Smoothing Inference with Twisted Objectivescited by 22
  12. 2021Improving Lossless Compression Rates via Monte Carlo Bits-Back Codingcited by 19
38 more
  1. 2021Online Variational Filtering and Parameter Learningcited by 19
  2. 2021Differentiable Particle Filtering without Modifying the Forward Passcited by 18
  3. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  4. 2021Stein Variational Gradient Descent: many-particle and long-time asymptoticscited by 15
  5. 2022Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptoticscited by 15
  6. 2024Inferring stochastic low-rank recurrent neural networks from neural datacited by 15
  7. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
  8. 2021Nested Variational Inferencecited by 14
  9. 2021Surrogate Likelihoods for Variational Annealed Importance Samplingcited by 14
  10. 2023Reduced-Order Autodifferentiable Ensemble Kalman Filterscited by 14
  11. 2021Variational Combinatorial Sequential Monte Carlo Methods for Bayesian Phylogenetic Inferencecited by 11
  12. 2021On Incorporating Inductive Biases into VAEscited by 11
  13. 2021Information is Power: Intrinsic Control via Information Capturecited by 11
  14. 2021Empirical Evaluation of Biased Methods for Alpha Divergence Minimizationcited by 10
  15. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
  16. 2023On the Identifiability of Switching Dynamical Systemscited by 9
  17. 2023Adaptive Annealed Importance Sampling with Constant Rate Progresscited by 7
  18. 2024Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inferencecited by 7
  19. 2021Learning Proposals for Probabilistic Programs with Inference Combinatorscited by 6
  20. 2021Variational Marginal Particle Filterscited by 6
  21. 2022Bounding Evidence and Estimating Log-Likelihood in VAEcited by 6
  22. 2023Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Frameworkcited by 6
  23. 2022Unsupervised representation learning with recognition-parametrised probabilistic modelscited by 5
  24. 2023Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systemscited by 5
  25. 2023Online Variational Sequential Monte Carlocited by 5
  26. 2022Variational Inference with Locally Enhanced Bounds for Hierarchical Modelscited by 4
  27. 2023NAS-X: Neural Adaptive Smoothing via Twistingcited by 4
  28. 2024Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Samplingcited by 4
  29. 2021An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulationscited by 3
  30. 2022Uphill Roads to Variational Tightness: Monotonicity and Monte Carlo Objectivescited by 3
  31. 2022Estimators of Entropy and Information via Inference in Probabilistic Modelscited by 3
  32. 2022Particle-Based Score Estimation for State Space Model Learning in Autonomous Drivingcited by 3
  33. 2023U-Statistics for Importance-Weighted Variational Inferencecited by 3
  34. 2023Convergence Analysis of Stochastic Gradient Descent with MCMC Estimatorscited by 3
  35. 2024The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantificationcited by 3
  36. 2022De-Sequentialized Monte Carlo: a parallel-in-time particle smoothercited by 2
  37. 2023Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplerscited by 2
  38. 2023Reparameterized Variational Rejection Samplingcited by 2

50 most cited of 91 All 91 (JSON)