Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data

Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt

2016-05-20Variational Inference

Abstract

We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models. Leveraging recent advances in Stochastic Gradient Variational Bayes, DVBF can overcome intractable inference distributions via variational inference. Thus, it can handle highly nonlinear input data with temporal and spatial dependencies such as image sequences without domain knowledge. Our experiments show that enabling backpropagation through transitions enforces state space assumptions and significantly improves information content of the latent embedding. This also enables realistic long-term prediction.

Related Papers

Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selection2025-07-15 Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference2025-06-26 VHU-Net: Variational Hadamard U-Net for Body MRI Bias Field Correction2025-06-23 Branching Stein Variational Gradient Descent for sampling multimodal distributions2025-06-16 Robust Recursive Fusion of Multiresolution Multispectral Images with Location-Aware Neural Networks2025-06-16 Variational Inference with Mixtures of Isotropic Gaussians2025-06-16 Robust Filtering -- Novel Statistical Learning and Inference Algorithms with Applications2025-06-13 Bayesian Probabilistic Matrix Factorization2025-06-11