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...

Celý popis

Podrobná bibliografia

Vydané v:	2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS) s. 603 - 614
Hlavní autori:	Balcan, Maria-Florina, Dick, Travis, Vitercik, Ellen
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 01.10.2018
Predmet:	algorithm design Approximation algorithms Clustering algorithms differentially private optimization Dispersion Greedy algorithms online optimization Optimization piecewise Lipschitz Pricing Privacy
ISSN:	2575-8454
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!