Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization

A crucial problem in modern data science is data-driven algorithm design, where the goal is to choose the best algorithm, or algorithm parameters, for a specific application domain. In practice, we often optimize over a parametric algorithm family, searching for parameters with high performance on a...

Full description

Bibliographic Details

Published in:	2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS) pp. 603 - 614
Main Authors:	Balcan, Maria-Florina, Dick, Travis, Vitercik, Ellen
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2018
Subjects:	algorithm design Approximation algorithms Clustering algorithms differentially private optimization Dispersion Greedy algorithms online optimization Optimization piecewise Lipschitz Pricing Privacy
ISSN:	2575-8454
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!