Computer Science – Learning
Scientific paper
2010-03-06
Computer Science
Learning
14 pages Submitted to COLT 2010
Scientific paper
Structured output prediction is an important machine learning problem both in theory and practice, and the max-margin Markov network (\mcn) is an effective approach. All state-of-the-art algorithms for optimizing \mcn\ objectives take at least $O(1/\epsilon)$ number of iterations to find an $\epsilon$ accurate solution. Recent results in structured optimization suggest that faster rates are possible by exploiting the structure of the objective function. Towards this end \citet{Nesterov05} proposed an excessive gap reduction technique based on Euclidean projections which converges in $O(1/\sqrt{\epsilon})$ iterations on strongly convex functions. Unfortunately when applied to \mcn s, this approach does not admit graphical model factorization which, as in many existing algorithms, is crucial for keeping the cost per iteration tractable. In this paper, we present a new excessive gap reduction technique based on Bregman projections which admits graphical model factorization naturally, and converges in $O(1/\sqrt{\epsilon})$ iterations. Compared with existing algorithms, the convergence rate of our method has better dependence on $\epsilon$ and other parameters of the problem, and can be easily kernelized.
Saha Ankan
Vishwanathan S. V. N.
Zhang Xinhua
No associations
LandOfFree
Faster Rates for training Max-Margin Markov Networks 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 Faster Rates for training Max-Margin Markov Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Faster Rates for training Max-Margin Markov Networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-269494