Back to Results
First PageMeta Content
Convex analysis / Operations research / Convex optimization / Convex function / Interior point method / Lipschitz continuity / Linear programming / Self-concordant function / Gradient descent / Mathematical optimization / Numerical analysis / Mathematical analysis


Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback Ankan Saha University of Chicago
Add to Reading List

Document Date: 2011-04-04 16:05:29

Open Document

File Size: 318,88 KB

Share Result on Facebook

Facility

Ambuj Tewari University of Texas / Bandit Feedback Ankan Saha University of Chicago / /

IndustryTerm

regret algorithms / self-concordance based algorithm / optimization algorithm / valid algorithms / bandit algorithms / online convex optimization / Online Smooth Convex Optimization / online linear optimization / online optimization / bandit algorithm / information algorithm / learning algorithms / /

Organization

University of Texas at Austin / University of Chicago / US Federal Reserve / Ambuj Tewari University / /

Person

Adam Tauman Kalai / Thomas P. Hayes / Alexander Rakhlin / Ofer Dekel / Varsha Dani / Robert D. Kleinberg / Lin Xiao / Alekh Agarwal / Satyen Kale / Jacob Abernethy / Arkadi S. Nemirovski / Michael J. Todd / Amit Agarwal / H. Brendan McMahan / Elad Hazan / Sham Kakade / Abraham Flaxman / /

Position

player / /

Product

Cowon D2+ Portable Audio Device / /

ProvinceOrState

Texas / /

PublishedMedium

Machine Learning / /

Technology

player algorithm / randomized algorithm / information algorithm / 4 ALGORITHM / self-concordance based algorithm / bandit algorithm / Machine Learning / information AHR algorithm / w∈K algorithm / Logarithmic regret algorithms / valid algorithms / optimization algorithm / Bandit OCO Algorithm / pdf / bandit algorithms / /

URL

http /

SocialTag