Select Lab Publications


Learning Structured Prediction Models: A Large Margin Approach (2005)

By: Ben Taskar, Vassil Chatalbashev, Daphne Koller, and Carlos Guestrin

Abstract: We consider large margin estimation in a broad range of prediction models where inference involves solving combinatorial optimization problems, for example, weighted graphcuts or matchings. Our goal is to learn parameters such that inference using the model reproduces correct answers on the training data. Our method relies on the expressive power of convex optimization problems to compactly capture inference or solution optimality in structured prediction models. Directly embedding this structure within the learning formulation produces concise convex problems for efficient estimation of very complex and diverse models. We describe experimental results on a matching task, disulfide connectivity prediction, showing significant improvements over state-of-the-art methods.

Download Information
Ben Taskar, Vassil Chatalbashev, Daphne Koller, and Carlos Guestrin (2005). "Learning Structured Prediction Models: A Large Margin Approach." 22nd International Conference on Machine Learning (ICML). pdf            
BibTeX citation

@inproceedings{Taskar+al:icml2005learning2x,
author = {Ben Taskar and Vassil Chatalbashev and Daphne Koller and Carlos Guestrin},
title = {Learning Structured Prediction Models: A Large Margin Approach},
booktitle = {22nd International Conference on Machine Learning (ICML)},
year = {2005},
address = {Bonn},
month = {August},
wwwfilebase = {icml2005-taskar-chatalbashev-koller-guestrin},
wwwtopic = {Supervised Learning}
}



full list