Stochastic automatic differentiation for Monte Carlo processes

Author:

Guilherme Catumba, Alberto Ramos, Bryan Zaldivar

Keyword:

High Energy Physics - Lattice, High Energy Physics - Lattice (hep-lat), Data Analysis, Statistics and Probability (physics.data-an), Machine Learning (stat.ML)

journal:

date:

2023-07-27 16:00:00

Abstract

Monte Carlo methods represent a cornerstone of computer science. They allow to sample high dimensional distribution functions in an efficient way. In this paper we consider the extension of Automatic Differentiation (AD) techniques to Monte Carlo process, addressing the problem of obtaining derivatives (and in general, the Taylor series) of expectation values. Borrowing ideas from the lattice field theory community, we examine two approaches. One is based on reweighting while the other represents an extension of the Hamiltonian approach typically used by the Hybrid Monte Carlo (HMC) and similar algorithms. We show that the Hamiltonian approach can be understood as a change of variables of the reweighting approach, resulting in much reduced variances of the coefficients of the Taylor series. This work opens the door to find other variance reduction techniques for derivatives of expectation values.

PDF: Stochastic automatic differentiation for Monte Carlo processes.pdf