Stability Enhanced Gaussian Process Variational Autoencoders
cs.LG, cs.SY, eess.SY
Submitted: 2026-04-10
Updated: 2026-09-18
Code: https://github.com/pnnl/COPIP
License: http://creativecommons.org/licenses/by/4.0/
The gist: A novel stability-enhanced Gaussian process variational autoencoder (SEGP-VAE) is proposed for indirectly training a low-dimensional linear time invariant (LTI) system, using high-dimensional video
Terminology
Abstract
A novel stability-enhanced Gaussian process variational autoencoder (SEGP-VAE) is proposed for indirectly training a low-dimensional linear time invariant (LTI) system, using high-dimensional video data. The mean and covariance function of the novel SEGP prior are derived from the definition of an LTI system, enabling the SEGP to capture the indirectly observed latent process using a combined probabilistic and interpretable physical model. The search space of LTI parameters is restricted to the set of semi-contracting systems via a complete and unconstrained parametrisation. As a result, the SEGP-VAE can be trained using unconstrained optimisation algorithms. Furthermore, this parametrisation prevents numerical issues caused by the presence of a non-Hurwitz state matrix. A case study applies SEGP-VAE to a dataset containing videos of spiralling particles. This highlights the benefits of the approach and the application-specific design choices that enabled accurate latent state predictions.
Sources
- Tutorial on Variational Autoencoders
- Visual anomaly detection in video by variational autoencoder
- Variational Message Passing with Structured Inference Networks
- tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Perspectives on Contractivity in Control, Optimization, and Learning
- Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
- Auto-Encoding Variational Bayes
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks