Saved in:
Bibliographic Details
Main Authors: Leme, Renato Purita Paes, Stein, Cliff, Teng, Yifeng, Worah, Pratik
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.18463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912245800239104
author Leme, Renato Purita Paes
Stein, Cliff
Teng, Yifeng
Worah, Pratik
author_facet Leme, Renato Purita Paes
Stein, Cliff
Teng, Yifeng
Worah, Pratik
contents We design efficient approximation algorithms for maximizing the expectation of the supremum of families of Gaussian random variables. In particular, let $\mathrm{OPT}:=\max_{σ_1,\cdots,σ_n}\mathbb{E}\left[\sum_{j=1}^{m}\max_{i\in S_j} X_i\right]$, where $X_i$ are Gaussian, $S_j\subset[n]$ and $\sum_iσ_i^2=1$, then our theoretical results include: - We characterize the optimal variance allocation -- it concentrates on a small subset of variables as $|S_j|$ increases, - A polynomial time approximation scheme (PTAS) for computing $\mathrm{OPT}$ when $m=1$, and - An $O(\log n)$ approximation algorithm for computing $\mathrm{OPT}$ for general $m>1$. Such expectation maximization problems occur in diverse applications, ranging from utility maximization in auctions markets to learning mixture models in quantitative genetics.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18463
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Allocating Variance to Maximize Expectation
Leme, Renato Purita Paes
Stein, Cliff
Teng, Yifeng
Worah, Pratik
Machine Learning
We design efficient approximation algorithms for maximizing the expectation of the supremum of families of Gaussian random variables. In particular, let $\mathrm{OPT}:=\max_{σ_1,\cdots,σ_n}\mathbb{E}\left[\sum_{j=1}^{m}\max_{i\in S_j} X_i\right]$, where $X_i$ are Gaussian, $S_j\subset[n]$ and $\sum_iσ_i^2=1$, then our theoretical results include: - We characterize the optimal variance allocation -- it concentrates on a small subset of variables as $|S_j|$ increases, - A polynomial time approximation scheme (PTAS) for computing $\mathrm{OPT}$ when $m=1$, and - An $O(\log n)$ approximation algorithm for computing $\mathrm{OPT}$ for general $m>1$. Such expectation maximization problems occur in diverse applications, ranging from utility maximization in auctions markets to learning mixture models in quantitative genetics.
title Allocating Variance to Maximize Expectation
topic Machine Learning
url https://arxiv.org/abs/2502.18463