Search all the public and authenticated articles in CiteULike.
Enter a search phrase. You can also specify

a CiteULike article id (123456),

a DOI (doi:10.1234/12345678)

or a PubMed Id (pmid:12345678).

Click Help for advanced usage.

CiteULike is a free online bibliography manager. Register and you can start organising your references online.

Online convex optimization in the bandit setting: gradient descent without a gradient

by: Abraham D. Flaxman, Adam T. Kalai, Brendan H. Mcmahan

In SODA '05: Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms (2005), pp. 385-394.

View the full article here:

ACM

This article has been bookmarked 4 times, initially on 2007-05-22.

2009-09-18	User idlebrain
	ml-bandit, al-soda, al-bandit
2008-09-16	User neddimitrov
	bandit, convex, online, optimization
2008-01-29	User hrishi
	bandit, game_theory, unread
2007-05-22	User abie
	and, approximation, convex, descent, exploit, explore, gradient, online, optimization, perturbation, simultaneous, stochastic

CiteULike organises scholarly (or academic) papers or literature and provides bibliographic (which means it makes bibliographies) for universities and higher education establishments. It helps undergraduates and postgraduates. People studying for PhDs or in postdoctoral (postdoc) positions. The service is similar in scope to EndNote or RefWorks or any other reference manager like BibTeX, but it is a social bookmarking service for scientists and humanities researchers.

convex	2
bandit	2
online	2
optimization	2
ml-bandit	1
simultaneous	1
and	1
al-bandit	1
stochastic	1
gradient	1
descent	1
al-soda	1
approximation	1
game_theory	1
exploit	1
perturbation	1
explore	1
unread	1

Online convex optimization in the bandit setting: gradient descent without a gradient

View the full article here:

Tag Summary