Improved sampling via learned diffusions
Recently, a series of papers proposed deep learning-based approaches to sample from
target distributions using controlled diffusion processes, being trained only on the …
target distributions using controlled diffusion processes, being trained only on the …
Solving high-dimensional Hamilton–Jacobi–Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Optimal control of diffusion processes is intimately connected to the problem of solving
certain Hamilton–Jacobi–Bellman equations. Building on recent machine learning inspired …
certain Hamilton–Jacobi–Bellman equations. Building on recent machine learning inspired …
An optimal control perspective on diffusion-based generative modeling
We establish a connection between stochastic optimal control and generative models based
on stochastic differential equations (SDEs), such as recently developed diffusion …
on stochastic differential equations (SDEs), such as recently developed diffusion …
Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning
One of the main challenges in molecular dynamics is overcoming the 'timescale barrier': in
many realistic molecular systems, biologically important rare transitions occur on timescales …
many realistic molecular systems, biologically important rare transitions occur on timescales …
Stein variational model predictive control
Decision making under uncertainty is critical to real-world, autonomous systems. Model
Predictive Control (MPC) methods have demonstrated favorable performance in practice …
Predictive Control (MPC) methods have demonstrated favorable performance in practice …
Data assimilation: the Schrödinger perspective
S Reich - Acta Numerica, 2019 - cambridge.org
Data assimilation addresses the general problem of how to combine model-based
predictions with partial and noisy observations of the process in an optimal manner. This …
predictions with partial and noisy observations of the process in an optimal manner. This …
Robust SDE-based variational formulations for solving linear PDEs via deep learning
Abstract The combination of Monte Carlo methods and deep learning has recently led to
efficient algorithms for solving partial differential equations (PDEs) in high dimensions …
efficient algorithms for solving partial differential equations (PDEs) in high dimensions …
Bayesian learning via neural Schrödinger–Föllmer flows
F Vargas, A Ovsianas, D Fernandes, M Girolami… - Statistics and …, 2023 - Springer
In this work we explore a new framework for approximate Bayesian inference in large
datasets based on stochastic control. We advocate stochastic control as a finite time and low …
datasets based on stochastic control. We advocate stochastic control as a finite time and low …
Transition path theory for Langevin dynamics on manifolds: Optimal control and data-driven solver
We present a data-driven point of view for rare events, which represent conformational
transitions in biochemical reactions modeled by overdamped Langevin dynamics on …
transitions in biochemical reactions modeled by overdamped Langevin dynamics on …
Stochastic control and nonequilibrium thermodynamics: Fundamental limits
Y Chen, TT Georgiou… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
We consider damped stochastic systems in a controlled (time varying) potential and study
their transition between specified Gibbs-equilibria states in finite time. By the second law of …
their transition between specified Gibbs-equilibria states in finite time. By the second law of …