# A General Method for Amortizing Variational Filtering

arXiv: https://arxiv.org/abs/1811.05090 · HTML: https://mlsanity.com/paper/1811.05090/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2018.

## Built on by (most cited first, 14 of 14)

- [Uncovering mesa-optimization algorithms in Transformers](https://mlsanity.com/paper/2309.05858/) (2023)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation](https://mlsanity.com/paper/2207.00787/) (2022)
- [Online Variational Filtering and Parameter Learning](https://mlsanity.com/paper/2110.13549/) (2021)
- [Revisiting Structured Variational Autoencoders](https://mlsanity.com/paper/2305.16543/) (2023)
- [Learning Optimal Filters Using Variational Inference](https://mlsanity.com/paper/2406.18066/) (2024)
- [Real-Time Variational Method for Learning Neural Trajectory and its Dynamics](https://mlsanity.com/paper/2305.11278/) (2023)
- [Variational excess risk bound for general state space models](https://mlsanity.com/paper/2312.09607/) (2023)
- [Tree-based variational inference for Poisson log-normal models](https://mlsanity.com/paper/2406.17361/) (2024)
- [A Metalearned Neural Circuit for Nonparametric Bayesian Inference](https://mlsanity.com/paper/2311.14601/) (2023)
- [Importance sampling for online variational learning](https://mlsanity.com/paper/2402.02859/) (2024)
- [Efficient Online Variational Estimation via Monte Carlo Sampling](https://mlsanity.com/paper/2602.06579/) (2026)
- [Neural Diffusion Intensity Models for Point Process Data](https://mlsanity.com/paper/2602.24083/) (2026)
- [Amortized backward variational inference in nonlinear state-space models](https://mlsanity.com/paper/2206.00319/) (2022)

## Abstract (arXiv)

We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information from only past and present variables, i.e. filtering. The algorithm is derived from the variational objective in the filtering setting and consists of an optimization procedure at each time step. By performing each inference optimization procedure with an iterative amortized inference model, we obtain a computationally efficient implementation of the algorithm, which we call amortized variational filtering. We present experiments demonstrating that this general-purpose method improves performance across several deep dynamical latent variable models.