Accelerated Flow for Probability distributions

01/10/2019
by   Amirhossein Taghvaei, et al.
0

This paper presents a methodology and numerical algorithms for constructing accelerated gradient flows on the space of probability distributions. In particular, we extend the recent variational formulation of accelerated gradient methods in (wibisono, et. al. 2016) from vector valued variables to probability distributions. The variational problem is modeled as a mean-field optimal control problem. The maximum principle of optimal control theory is used to derive Hamilton's equations for the optimal gradient flow. The Hamilton's equation are shown to achieve the accelerated form of density transport from any initial probability distribution to a target probability distribution. A quantitative estimate on the asymptotic convergence rate is provided based on a Lyapunov function construction, when the objective functional is displacement convex. Two numerical approximations are presented to implement the Hamilton's equations as a system of N interacting particles. The continuous limit of the Nesterov's algorithm is shown to be a special case with N=1. The algorithm is illustrated with numerical examples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/16/2019

Mean-field Langevin System, Optimal Control and Deep Neural Networks

In this paper, we study a regularised relaxed optimal control problem an...
research
12/02/2019

On the geometry of Stein variational gradient descent

Bayesian inference problems require sampling or approximating high-dimen...
research
12/13/2022

Optimal control of nonlocal continuity equations: numerical solution

The paper addresses an optimal ensemble control problem for nonlocal con...
research
03/29/2022

A Derivation of Nesterov's Accelerated Gradient Algorithm from Optimal Control Theory

Nesterov's accelerated gradient algorithm is derived from first principl...
research
02/07/2020

Wasserstein Proximal Gradient

We consider the task of sampling from a log-concave probability distribu...
research
06/10/2020

Gradient Flows for Regularized Stochastic Control Problems

This work is motivated by a desire to extend the theoretical underpinnin...
research
08/01/2022

A Particle-Based Algorithm for Distributional Optimization on Constrained Domains via Variational Transport and Mirror Descent

We consider the optimization problem of minimizing an objective function...

Please sign up or login with your details

Forgot password? Click here to reset