Method for machine learning using online convex optimization...

Details Method for machine learning using online convex optimization... Method for machine learning using online convex optimization...

2011-01-11

2011-01-11

Sparks, Donald (Department: 2129)

Data processing: artificial intelligence

Machine learning

C706S019000

Reexamination Certificate

active

07870082

ABSTRACT:
Methods, systems, and computer program products are provided for the online convex optimization problem, in which the decision maker has knowledge of the all past states and resulting cost functions for his previous choices and attempts to make a new choice that results in minimum regret. The method does not rely upon the structure of the cost function or the characterization of the states and takes advantage of the similarity between successive states to enable the method to converge to a reasonably optimal result.

REFERENCES:
Zinkevich, Online Convex Programming and Generalized Infinitesimal Gradient Ascent, 2003.
Dani et al., Robbing the bandit: Less regret in online geometric optimization against an adaptive adversary, Nov. 12, 2005.
Adam Kalai et al., Efficient algorithms for online decision problems, Journal of Computer and System Sciences 71, 291-307, 2005.
Beg et al., Some Fixed Point Theorems in Convex Metric Spaces, 1991.
Office Action dated Sep. 17, 2009 from U.S. Appl. No. 12/134,073.

Affiliated with

Also associated with

Rating

Method for machine learning using online convex optimization... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method for machine learning using online convex optimization..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for machine learning using online convex optimization... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2732050