BIMSA > Seminar on Control Theory and Nonlinear Filtering Some advanced results in the Synthetic Control
Some advanced results in the Synthetic Control
Organizer
Shing Toung Yau
Speaker
Jia Yi Kang
Time
Friday, December 1, 2023 9:00 PM - 9:30 PM
Venue
Online
Abstract
In this report, I will introduce some studies of a machine learning-based estimator as a control variate for mitigating the variance of Monte Carlo sampling. Specifically, they seek to uncover the key factors that influence the efficiency of control variates in reducing variance. They examine a prototype estimation problem that involves simulating the moments of a Sobolev function based on observations obtained from (random) quadrature nodes. Firstly, they establish an information-theoretic lower bound for the problem. They then study a specific quadrature rule that employs a nonparametric regression-adjusted control variate to reduce the variance of the Monte Carlo simulation.