3 papers
cs.LG2026
Separating Geometry from Probability in the Analysis of Generalization
Maxim Raginsky, Benjamin Recht
The goal of machine learning is to find models that minimize prediction error on data that has not yet been seen. Its operational paradigm assumes access to a dataset and artic…
math.OC2024
A variational approach to sampling in diffusion processes
Maxim Raginsky
We revisit the work of Mitter and Newton on an information-theoretic interpretation of Bayes' formula through the Gibbs variational principle. This formulation allowed them to pose…
math.OC2024
Some Remarks on Controllability of the Liouville Equation
Maxim Raginsky
We revisit the work of Roger Brockett on controllability of the Liouville equation, with a particular focus on the following problem: Given a smooth controlled dynamical system of…