Back to Results
First PageMeta Content
Statistics / Stability / Lipschitz continuity / Convex function / Loss function / Mathematical optimization / Linear programming / Continuous function / Operations research / Mathematical analysis / Mathematics


The Interplay Between Stability and Regret in Online Learning Ankan Saha Department of Computer Science University of Chicago
Add to Reading List

Document Date: 2012-12-03 21:04:12


Open Document

File Size: 268,22 KB

Share Result on Facebook

Company

Microsoft / /

Country

United States / /

/

Facility

stable ERM / /

IndustryTerm

Online Linear Programming / respective algorithms / proximal type algorithms / bounded regret algorithm / online learning method / online case / canonical learning algorithm / Online learning / online learning framework / dot product / online learning setup / online learning algorithms / online learning conditions / mirror descent algorithms / online setting / online stability / online learnability / stable algorithm / arbitrary online learning algorithms / online adversarial setting / namely online stability / stable online learning algorithms / online stable algorithm / mirror descent algorithm / online learning setting / online stable / online algorithm / intuitive algorithm / online learning algorithm / online algorithms / online learning game / online stability condition / learning algorithms / /

Organization

University of Michigan / Online Learning Ankan Saha Department / University of Chicago / /

Person

Forward Regret / /

Position

Follow-The-Leader / Follow The Leader / player / Follow-The-Regularized-Leader / Follow The Regularized Leader / /

Product

Latte W10 Portable Audio Device / Cowon D2+ Portable Audio Device / /

ProgrammingLanguage

C / L / /

ProvinceOrState

Michigan / /

Technology

stable algorithm / online algorithm / three algorithms / online stable algorithm / alternative stable algorithm / existing OCP algorithms / canonical learning algorithm / FTL algorithm / FOBOS mirror descent algorithm / existing online algorithms / arbitrary online learning algorithms / two algorithms / bounded regret algorithm / online learning algorithm / online algorithms / proximal type algorithms / respective algorithms / stable online learning algorithms / online learning algorithms / mirror descent algorithms / FTRL algorithms / intuitive algorithm / /

SocialTag