Data to 14 Oct 2026

Deep Kalman Filters

arXiv 1511.05121 ↗First posted 16 Nov 2015stat.ML cs.LGcited by 166

Not on the map. Why?

Abstract (arXiv)

Kalman Filters are one of the most influential models of time-varying phenomena. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption in a variety of disciplines. Motivated by recent variational methods for learning deep generative models, we introduce a unified algorithm to efficiently learn a broad spectrum of Kalman filters. Of particular interest is the use of temporal generative models for counterfactual inference. We investigate the efficacy of such models for counterfactual inference, and to that end we introduce the "Healing MNIST" dataset where long-term structure, noise and actions are applied to sequences of digits. We show the efficacy of our method for modeling this dataset. We further show how our model can be used for counterfactual inference for patients, based on electronic health record data of 8,000 patients over 4.5 years.

Key facts. Cited by 166 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 26; 2023: 26; 2024: 30; 2025: 17; 2026: 39.

166 papers.

Sort:

By area:

2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 132
2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
2023Score-based Data Assimilationcited by 96
2022Criteria for Classifying Forecasting Methodscited by 48
2021Clockwork Variational Autoencoderscited by 42
2021Universal Approximation Theorems for Differentiable Geometric Deep Learningcited by 41
2021Contrastively Disentangled Sequential Variational Autoencodercited by 34
2023Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecastingcited by 34
2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 31

38 more

2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Seriescited by 29
2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
2021Roto-translated Local Coordinate Frames For Interacting Dynamical Systemscited by 24
2022Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysiscited by 22
2026Generative Recursive Reasoningcited by 20
2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 18
2021Unsupervised Learned Kalman Filteringcited by 17
2021ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equationscited by 15
2021SSDNet: State Space Decomposition Neural Network for Time Series Forecastingcited by 15
2022An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Contextcited by 15
2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
2024Automatically Learning Hybrid Digital Twins of Dynamical Systemscited by 14
2022Latent State Marginalization as a Low-cost Approach for Improving Explorationcited by 13
2022On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learningcited by 13
2021Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertaintycited by 11
2021Information is Power: Intrinsic Control via Information Capturecited by 11
2023Revisiting Structured Variational Autoencoderscited by 11
2021Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correctioncited by 10
2021Learning to Assimilate in Chaotic Dynamical Systemscited by 10
2022Learning Robust Dynamics through Variational Sparse Gatingcited by 8
2022The future is different: Large pre-trained language models fail in prediction taskscited by 8
2023Neural Dynamic Focused Topic Modelcited by 8
2024State-observation augmented diffusion model for nonlinear assimilation with unknown dynamicscited by 8
2024Meta-Dynamical State Space Models for Integrative Neural Data Analysiscited by 8
2025BRAID: Input-Driven Nonlinear Dynamical Modeling of Neural-Behavioral Datacited by 8
2026Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Trackingcited by 8
2024eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modelingcited by 7
2024Learning Action-based Representations Using Invariancecited by 7
2024Temporal Test-Time Adaptation with State-Space Modelscited by 7
2021VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Expertscited by 6
2021Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shootingcited by 6
2022Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Datacited by 6
2024Deep Bayesian Filter for Bayes-faithful Data Assimilationcited by 6
2022Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filteringcited by 5
2022Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structurescited by 5
2022Phi-DVAE: Physics-Informed Dynamical Variational Autoencoders for Unstructured Data Assimilationcited by 5

50 most cited of 166 All 166 (JSON)