arXiv Machine Learning
Information-theoretic receding-horizon active learning of nonlinear dynamical systems
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
5d ago
Information-theoretic receding-horizon active learning of nonlinear dynamical systems
Accurately learning nonlinear dynamics from a finite-duration experiment requires the efficient collection of informative data. We address this challenge for stochastic controlled nonlinear dynamical...
arXiv Machine Learning
Sep 15
Active Learning with Bayesian Multi-Fidelity Laplace Neural Operators for Oscillatory Parametric PDEs
arXiv:2502.00550v2 Announce Type: replace Abstract: Surrogate models of parametric dynamical systems are essential for many-query and real-time predictions in engineering applications such as design...
arXiv Machine Learning
Sep 22
PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems
arXiv:2609.24117v1 Announce Type: new Abstract: Identifying linear time-invariant (LTI) dynamical systems is challenging when trajectories are short, noisy, or high-dimensional. Traditional system id...
arXiv Machine Learning
Sep 23
BOBA: Dynamic Bayesian Optimization through Bayesian Active Inference
arXiv:2609.26021v1 Announce Type: new Abstract: Dynamic black-box optimization presents significant challenges for Bayesian Optimization (BO), as the objective function evolves over time, causing opt...
arXiv Statistics ML
Sep 11
Learning-Based Surrogate Method for Stochastic Optimization under Decision-Dependent Uncertainty with Adaptive Random Designs
The paper introduces a learning-based surrogate approach for stochastic optimization problems where uncertainty depends on the decision, modeled via a nonparametric regression. It constructs a surrogate that embeds iteratively updated Jacobian estimates, using an adaptive random design that focuses sampling near the current iterate to achieve dimension‑independent convergence of the Jacobian estimates. The resulting learning‑based stochastic prox‑linear (L‑SPL) algorithm demonstrates nonasymptotic convergence rates and outperforms existing methods in sample efficiency and objective value in numerical experiments.
arXiv Machine Learning
Jul 27
On the Identifiability of Controlled World Models
arXiv:2607. 22430v1 Announce Type: new Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to planning and control.