학술논문

Efficient Unbiased Sparsification
Document Type
Working Paper
Source
Subject
Computer Science - Information Theory
Computer Science - Machine Learning
Mathematics - Statistics Theory
Language
Abstract
An unbiased $m$-sparsification of a vector $p\in \mathbb{R}^n$ is a random vector $Q\in \mathbb{R}^n$ with mean $p$ that has at most $m