paper-with-me

홈 › Papers

Meta-learning Control Variates: Variance Reduction with Limited Data

2023-03-08 · Zhuo Sun, Chris J. Oates, François-Xavier Briol

Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but constructing effective control variates can be challenging when the number of samples is small. In this paper, we show that when a large number of related integrals need to be computed, it is possible to leverage the similarity between these integration tasks to improve performance even when the number of samples per task is very small. Our approach, called meta learning CVs (Meta-CVs), can be used for up to hundreds or thousands of tasks. Our empirical assessment indicates that Meta-CVs can lead to significant variance reduction in such settings, and our theoretical analysis establishes general conditions under which Meta-CVs can be successfully trained.

📄 PDF Abstract BibTeX arXiv:2303.04756

Code (1)

jz-fun/meta_control_variates 공식 구현 pytorch

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Theoretical guarantees for neural control variates in MCMC

2023-04-03 · Denis Belomestny, Artur Goldman, Alexey Naumov, Sergey Samsonov

In this paper, we propose a variance reduction approach for Markov chains based on additive control variates and the minimization of an appropriate estimate for the asymptotic variance. We focus on the particular case wh…

Pathwise Gradient Variance Reduction with Control Variates in Variational Inference

2024-10-08 · Kenyon Ng, Susan Wei

Variational inference in Bayesian deep learning often involves computing the gradient of an expectation that lacks a closed-form solution. In these cases, pathwise and score-function gradient estimators are the most comm…

Variational Inference

Neural Control Variates for Variance Reduction

2018-06-01 · Ruosi Wan, Mingjun Zhong, Haoyi Xiong, Zhanxing Zhu

In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications. …

Reinforcement Learning

Coordinate-wise Control Variates for Deep Policy Gradients

2021-07-11 · Yuanyi Zhong, Yuan Zhou, Jian Peng

The control variates (CV) method is widely used in policy gradient estimation to reduce the variance of the gradient estimators in practice. A control variate is applied by subtracting a baseline function from the state-…

continuous-controlContinuous Control

Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution

2019-11-22 · Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto 외

Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates. Modern variance reduction techniques mostly consider categorical distri…