# De-Sequentialized Monte Carlo: a parallel-in-time particle smoother

arXiv: https://arxiv.org/abs/2202.02264 · HTML: https://mlsanity.com/paper/2202.02264/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 74 references that are in the map.
- First posted on arXiv 4 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Variational Sequential Monte Carlo](https://mlsanity.com/paper/1705.11140/) (2017)
- [Filtering Variational Objectives](https://mlsanity.com/paper/1705.09279/) (2017)
- [Auto-Encoding Sequential Monte Carlo](https://mlsanity.com/paper/1705.10306/) (2017)
- [Differentiable Particle Filtering via Entropy-Regularized Optimal Transport](https://mlsanity.com/paper/2102.07850/) (2021)
- [Temporal Parallelization of Bayesian Smoothers](https://mlsanity.com/paper/1905.13002/) (2019)
- [Particle Gibbs with Ancestor Sampling](https://mlsanity.com/paper/1401.0604/) (2014)
- [Tensor Monte Carlo: particle methods for the GPU era](https://mlsanity.com/paper/1806.08593/) (2018)
- [Divide-and-Conquer with Sequential Monte Carlo](https://mlsanity.com/paper/1406.4993/) (2014)
- [Unbiased Smoothing using Particle Independent Metropolis-Hastings](https://mlsanity.com/paper/1902.01781/) (2019)
- [Parallel Iterated Extended and Sigma-point Kalman Smoothers](https://mlsanity.com/paper/2102.00514/) (2021)
- [Temporal Parallelization of Inference in Hidden Markov Models](https://mlsanity.com/paper/2102.05743/) (2021)
- [Product-form estimators: exploiting independence to scale up Monte Carlo](https://mlsanity.com/paper/2102.11575/) (2021)
- [Parallel resampling in the particle filter](https://mlsanity.com/paper/1301.4019/) (2013)
- [The divide-and-conquer sequential Monte Carlo algorithm: theoretical properties and limit theorems](https://mlsanity.com/paper/2110.15782/) (2021)
- [Smoothing with Couplings of Conditional Particle Filters](https://mlsanity.com/paper/1701.02002/) (2017)
- [The Coupled Rejection Sampler](https://mlsanity.com/paper/2201.09585/) (2022)
- [Tree-based Particle Smoothing Algorithms in a Hidden Markov Model](https://mlsanity.com/paper/1808.08400/) (2018)

## Built on by (most cited first, 2 of 2)

- [Auxiliary MCMC and particle Gibbs samplers for parallelisable inference in latent dynamical systems](https://mlsanity.com/paper/2303.00301/) (2023)
- [Efficient Learning of Deep State Space Models via Importance Smoothing](https://mlsanity.com/paper/2605.21108/) (2026)

## Abstract (arXiv)

Particle smoothers are SMC (Sequential Monte Carlo) algorithms designed to approximate the joint distribution of the states given observations from a state-space model. We propose dSMC (de-Sequentialized Monte Carlo), a new particle smoother that is able to process T observations in O(log T) time on parallel architecture. This compares favourably with standard particle smoothers, the complexity of which is linear in T. We derive Lp convergence results for dSMC, with an explicit upper bound, polynomial in T. We then discuss how to reduce the variance of the smoothing estimates computed by dSMC by (i) designing good proposal distributions for sampling the particles at the initialization of the algorithm, as well as by (ii) using lazy resampling to increase the number of particles used in dSMC. Finally, we design a particle Gibbs sampler based on dSMC, which is able to perform parameter inference in a state-space model at a O(log(T)) cost on parallel hardware.