When can Regression-Adjusted Control Variates Help? Rare Events, Sobolev Embedding and Minimax Optimality
May 25, 2023 Β· Declared Dead Β· π Neural Information Processing Systems
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Jose Blanchet, Haoxuan Chen, Yiping Lu, Lexing Ying
arXiv ID
2305.16527
Category
math.ST
Cross-listed
cs.IT,
math.NA,
stat.ML
Citations
6
Venue
Neural Information Processing Systems
Last Checked
6 months ago
Abstract
This paper studies the use of a machine learning-based estimator as a control variate for mitigating the variance of Monte Carlo sampling. Specifically, we seek to uncover the key factors that influence the efficiency of control variates in reducing variance. We examine a prototype estimation problem that involves simulating the moments of a Sobolev function based on observations obtained from (random) quadrature nodes. Firstly, we establish an information-theoretic lower bound for the problem. We then study a specific quadrature rule that employs a nonparametric regression-adjusted control variate to reduce the variance of the Monte Carlo simulation. We demonstrate that this kind of quadrature rule can improve the Monte Carlo rate and achieve the minimax optimal rate under a sufficient smoothness assumption. Due to the Sobolev Embedding Theorem, the sufficient smoothness assumption eliminates the existence of rare and extreme events. Finally, we show that, in the presence of rare and extreme events, a truncated version of the Monte Carlo algorithm can achieve the minimax optimal rate while the control variate cannot improve the convergence rate.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β math.ST
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists
R.I.P.
π»
Ghosted
Minimax Optimal Procedures for Locally Private Estimation
R.I.P.
π»
Ghosted
Optimal Best Arm Identification with Fixed Confidence
R.I.P.
π»
Ghosted
Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees
R.I.P.
π»
Ghosted
User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted