mlsanityData to 14 Oct 2026

Linear Variational State-Space Filtering

arXiv 2201.01353 ↗First posted 4 Jan 2022cs.LG cs.CV cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce Variational State-Space Filters (VSSF), a new method for unsupervised learning, identification, and filtering of latent Markov state space models from raw pixels. We present a theoretically sound framework for latent state space inference under heterogeneous sensor configurations. The resulting model can integrate an arbitrary subset of the sensor measurements used during training, enabling the learning of semi-supervised state representations, thus enforcing that certain components of the learned latent state space to agree with interpretable measurements. From this framework we derive L-VSSF, an explicit instantiation of this model with linear latent dynamics and Gaussian distribution parameterizations. We experimentally demonstrate L-VSSF's ability to filter in latent space beyond the sequence length of the training dataset across several different test environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 4 Jan 2022.

Builds on

23 of 35 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  6. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  7. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  8. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  9. 2017Lossy Image Compression with Compressive Autoencoderscited by 294
  10. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 274
  11. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 264
  12. 2018Stochastic Video Generation with a Learned Priorcited by 245
11 more
  1. 2017Stochastic Variational Video Predictioncited by 234
  2. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
  3. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  4. 2015Deep Kalman Filterscited by 166
  5. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 156
  6. 2020Self-Supervised Visual Representation Learning from Hierarchical Groupingcited by 63
  7. 2017Robust Locally-Linear Controllable Embeddingcited by 38
  8. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  9. 2021Online Variational Filtering and Parameter Learningcited by 19
  10. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
  11. 2020An Auto-Encoder Strategy for Adaptive Image Segmentationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Self-Supervised Inference in State-Space Models
  2. 2024Variational quantization for state space models
  3. 2026On the Relation of State Space Models and Hidden Markov Models
  4. 2026Efficient Learning of Deep State Space Models via Importance Smoothing
  5. 2023Spectral State Space Models
  6. 2025TrackDiffuser: Nearly Model-Free Bayesian Filtering with Diffusion Model
  7. 2023Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems
  8. 2022Amortized backward variational inference in nonlinear state-space models