arXiv Machine Learning
Generalization as a robust performance property of learning-enabled 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
arXiv Machine Learning
Aug 14
On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective
arXiv:2608. 13510v1 Announce Type: cross Abstract: Machine learning procedures are commonly evaluated in terms of predictive accuracy and computational efficiency.
arXiv Machine Learning
Jun 29
PAC-Bayesian Certificates for Quadratic Closed-Loop Control
arXiv:2606. 28281v1 Announce Type: cross Abstract: PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objective is a quadratic trajectory cost.
arXiv Machine Learning
Jul 3
A Unified Lyapunov-IQC Framework for Uniform Stability of Smooth Quadratic First-Order Accelerated Optimizers
arXiv:2605. 08488v2 Announce Type: replace-cross Abstract: We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $\beta$-smooth and $\gamma$-strongly convex regime.
arXiv Machine Learning
Jun 24
Hessian-augmented Supervised Learning for Hamilton-Jacobi-Bellman PDEs
arXiv:2606. 23827v1 Announce Type: cross Abstract: A data-driven method is developed for approximating value functions in deterministic optimal control problems with nonlinear control-affine dynamics.
arXiv Machine Learning
Jul 9
Mathematical methods of reinforcement learning
arXiv:2607. 06935v1 Announce Type: cross Abstract: Reinforcement learning (RL) is increasingly grounded in tools from probability, optimization, and operator theory.
arXiv Machine Learning
Jun 5
Learning to optimize with guarantees: a complete characterization of linearly convergent algorithms
arXiv:2508. 00775v2 Announce Type: replace-cross Abstract: The design of many classical optimization algorithms is driven by the certification of linear convergence rates over classes of optimization problems.