On Local Entropy, Stochastic Control, and Deep Neural Networks
Author:
- 11 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 7, 437-441
Abstract
In this paper, we connect some recent papers on smoothing of energy landscapes and scored-based generative models of machine learning to classical work in stochastic control. We clarify these connections providing rigorous statements and representations which may serve as guidelines for further learning models.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- On the Relation Between Optimal Transport and Schrödinger Bridges: A Stochastic Control ViewpointJournal of Optimization Theory and Applications, 2015
- Optimal steering of inertial particles diffusing anisotropically with losses2015
- A survey of the Schrödinger problem and some of its connections with optimal transportDiscrete and Continuous Dynamical Systems, 2014
- Clustering and Classification through Normalizing Flows in Feature SpaceMultiscale Modeling & Simulation, 2010
- Logarithmic transformations and stochastic control2005
- On Free Energy, Stochastic Control, and Schrödinger Processes1991
- Variational path-integral representations for the density of a diffusion processStochastics and Stochastic Reports, 1989
- Stochastic control and nonequilibrium thermodynamical systemsApplied Mathematics & Optimization, 1989
- Stochastic variational formula for fundamental solutions of parabolic PDEApplied Mathematics & Optimization, 1985
- Stochastic calculus of variations and mechanicsJournal of Optimization Theory and Applications, 1983