Solving data-driven problems requires defining complex models and fitting them to data, neural networks being a motivating example. The fitting procedure can be seen as an optimization problem, which is often non-convex, and hence optimization guarantees are hard to derive. An opportunity is provided by viewing the mod...
Cristian Vega, C. Molinari, Lorenzo Rosasco et al.· 0 citations
This work first focuses on estimating the optimal one-step prediction function by nonlinear least squares, and derive high-probability guarantees measured with respect to the invariant measure of the process, and extends the framework to higher-order systems and finite-state spaces.
Oleksii Kachaiev, S. Villa, Lorenzo Rosasco· arXiv.org· 0 citations
We study Langevin-based methods for non-convex optimization under smoothness and dissipativity assumptions. Our focus is on obtaining non-asymptotic bounds for the expected excess risk rather than sampling guarantees for the full target distribution. The key ingredient of our analysis is a direct passage from relative...
E. Naldi, Marco Rando, Lorenzo Rosasco et al.· 0 citations
This work quantifies the sub-optimality of the model predictive control strategy, both in the case of exact Koopman dynamics, and in the case of learned ones, in the case of model predictive control systems with finite action spaces.
Edoardo Caldarelli, Oleksii Kachaiev, C. Molinari et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
