# Neural Adaptive Sequential Monte Carlo

arXiv: https://arxiv.org/abs/1506.03338 · HTML: https://mlsanity.com/paper/1506.03338/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2015.

## Built on by (most cited first, 30 of 34)

- [Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo](https://mlsanity.com/paper/2404.17546/) (2024)
- [Challenges and Opportunities in High-dimensional Variational Inference](https://mlsanity.com/paper/2103.01085/) (2021)
- [SIXO: Smoothing Inference with Twisted Objectives](https://mlsanity.com/paper/2206.05952/) (2022)
- [RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting](https://mlsanity.com/paper/2106.06064/) (2021)
- [Critic Sequential Monte Carlo](https://mlsanity.com/paper/2205.15460/) (2022)
- [On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2210.09256/) (2022)
- [HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling](https://mlsanity.com/paper/2110.02344/) (2021)
- [Learning to Assimilate in Chaotic Dynamical Systems](https://mlsanity.com/paper/2111.01058/) (2021)
- [KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty](https://mlsanity.com/paper/2406.15131/) (2024)
- [Low-Rank Constraints for Fast Inference in Structured Models](https://mlsanity.com/paper/2201.02715/) (2022)
- [Transport Score Climbing: Variational Inference Using Forward KL and Adaptive Neural Transport](https://mlsanity.com/paper/2202.01841/) (2022)
- [A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication](https://mlsanity.com/paper/2108.04436/) (2021)
- [Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference](https://mlsanity.com/paper/2403.10610/) (2024)
- [Trust-Region Twisted Policy Improvement](https://mlsanity.com/paper/2504.06048/) (2025)
- [Recurrent Neural Networks and Universal Approximation of Bayesian Filters](https://mlsanity.com/paper/2211.00335/) (2022)
- [Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests](https://mlsanity.com/paper/2302.12024/) (2023)
- [Online Variational Sequential Monte Carlo](https://mlsanity.com/paper/2312.12616/) (2023)
- [SPO: Sequential Monte Carlo Policy Optimisation](https://mlsanity.com/paper/2402.07963/) (2024)
- [Quasi-Bayes meets Vines](https://mlsanity.com/paper/2406.12764/) (2024)
- [NAS-X: Neural Adaptive Smoothing via Twisting](https://mlsanity.com/paper/2308.14864/) (2023)
- [Probabilistic Programming with Programmable Variational Inference](https://mlsanity.com/paper/2406.15742/) (2024)
- [Tracking large chemical reaction networks and rare events by neural networks](https://mlsanity.com/paper/2512.10309/) (2025)
- [The NFLikelihood: an unsupervised DNNLikelihood from Normalizing Flows](https://mlsanity.com/paper/2309.09743/) (2023)
- [Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage](https://mlsanity.com/paper/2505.19431/) (2025)
- [Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Series](https://mlsanity.com/paper/2105.09801/) (2021)
- [Optimization of Annealed Importance Sampling Hyperparameters](https://mlsanity.com/paper/2209.13226/) (2022)
- [VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning](https://mlsanity.com/paper/2602.18857/) (2026)
- [Fast ABC with joint generative modelling and subset simulation](https://mlsanity.com/paper/2104.08156/) (2021)
- [Worst-Case Analysis is Maximum-A-Posteriori Estimation](https://mlsanity.com/paper/2310.09774/) (2023)
- [Learning state and proposal dynamics in state-space models using differentiable particle filters and neural networks](https://mlsanity.com/paper/2411.15638/) (2024)

## Abstract (arXiv)

Sequential Monte Carlo (SMC), or particle filtering, is a popular class of methods for sampling from an intractable target distribution using a sequence of simpler intermediate distributions. Like other importance sampling-based methods, performance is critically dependent on the proposal distribution: a bad proposal can lead to arbitrarily inaccurate estimates of the target distribution. This paper presents a new method for automatically adapting the proposal using an approximation of the Kullback-Leibler divergence between the true posterior and the proposal distribution. The method is very flexible, applicable to any parameterized proposal distribution and it supports online and batch variants. We use the new framework to adapt powerful proposal distributions with rich parameterizations based upon neural networks leading to Neural Adaptive Sequential Monte Carlo (NASMC). Experiments indicate that NASMC significantly improves inference in a non-linear state space model outperforming adaptive proposal methods including the Extended Kalman and Unscented Particle Filters. Experiments also indicate that improved inference translates into improved parameter learning when NASMC is used as a subroutine of Particle Marginal Metropolis Hastings. Finally we show that NASMC is able to train a latent variable recurrent neural network (LV-RNN) achieving results that compete with the state-of-the-art for polymorphic music modelling. NASMC can be seen as bridging the gap between adaptive SMC methods and the recent work in scalable, black-box variational inference.