arXiv Machine Learning

Learning Stabilizing Latent Feedback Controllers via Multi-Step Backward Losses

arXiv:2610. 40931v1 Announce Type: cross Abstract: Can learned latent dynamics models support the design of feedback controllers that provably stabilize the original system?

arXiv Machine Learning
Oct 23

Verification of Unknown Dynamical Systems via Autoencoder Latent Space

The paper presents a formal method for verifying high‑dimensional dynamical systems by reducing dimensionality with convex autoencoders and learning latent dynamics via a kernel‑based approach. It constructs a finite abstraction in the latent space that provably contains all true behaviors of the original system, allowing verification results to be mapped back to the original system. Experiments on several systems, including a 26‑dimensional neural‑network‑controlled system, demonstrate significant scalability improvements.

By Robert Reed, Luca Laurenti, Morteza Lahijanian
arXiv Machine Learning
Oct 5

Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings

The paper introduces a hierarchical model-based reinforcement learning framework that learns control policies from action-free time series by exploiting shared dynamics across related systems. It uses low-dimensional dynamical embeddings to capture both shared structure and individual variation, which then parameterize shared policy and value networks. Experiments on Lorenz-63, double-pendulum, and neural-behavioral data show that these hierarchical policies outperform independently trained ones, achieve higher rewards than planning with the same models, and generalize to unseen systems using only embedding inference.

By Niklas Emonds, Georgia Koppe
Hugging Face Trending Papers
Jun 3

Learning Control-Affine Reduced-Order Models via Autoencoders

We present in this paper a framework for the identification of control-affine reduced-order models (ROMs). The proposed method utilizes autoencoders (AEs) to transform the high-dimensional states, and potentially the high-dimensional inputs, into reduced latent ones suitable for control-affine state-space dynamics.

arXiv Machine Learning
Nov 2

PCD: Predictive Coding Dynamics for Irregularly Sampled Time Series

The paper introduces Predictive Coding Dynamics (PCD), a residual feedback mechanism designed for irregularly sampled continuous-time series. PCD retains previous reconstructions, predicts observed entries, and uses masked signed residuals as an energy penalty to refine latent state recognition. Implemented with ODE-RNN and Latent ODE, it supports event-based hidden updates and improves forecasting and trajectory recovery under sparse, irregular sampling.

By Tianrui Gou, Jiayangmei Xu, Xingzhou Zhang, Lei Sha