Computer Science – Learning
Scientific paper
2010-02-25
Computer Science
Learning
Scientific paper
We analyze and evaluate an online gradient descent algorithm with adaptive per-coordinate adjustment of learning rates. Our algorithm can be thought of as an online version of batch gradient descent with a diagonal preconditioner. This approach leads to regret bounds that are stronger than those of standard online gradient descent for general online convex optimization problems. Experimentally, we show that our algorithm is competitive with state-of-the-art algorithms for large scale machine learning problems.
McMahan Brendan H.
Streeter Matthew
No associations
LandOfFree
Less Regret via Online Conditioning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Less Regret via Online Conditioning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Less Regret via Online Conditioning will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-288670