Work

Sharp bounds for population recovery

Year: 2017

Type: preprint

Abstract: The population recovery problem is a basic problem in noisy unsupervised learning that has attracted significant research attention in recent years [WY12,DRWY12, MS13, BIMP13, LZ15,DST16]. A number of different variants of this problem have been studied, often under assumptions on the unknown distribution (such as that it has restricted support size). In this work we study the sample complexity and algorithmic complexity of the most general version of the problem, under both bit-flip noise and erasure noise model. We give essentially matching upper and lower sample complexity bounds for both noise models, and efficient algorithms matching these sample complexity bounds up to polynomial factors.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1703.01474

Authors: De, Anindya, O'Donnell, Ryan, Servedio, Rocco

Institutions: Northwestern University, Carnegie Mellon University, Columbia University

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: AF: Small: Linear and Polynomial Threshold Functions: Structural Analysis and Algorithmic Applications, AF: Medium: Collaborative Research: Circuit Lower Bounds via Projections, AF: Small: Harmonic Analysis for Quantum Complexity

OpenAlex ID: W2593715710

Cites: 11

Cited by: 5

Related to: 10