Robust trainability of single neurons
Journal of Computer and System Sciences
Solving the multiple instance problem with axis-parallel rectangles
Artificial Intelligence
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Learning as search optimization: approximate large margin methods for structured prediction
ICML '05 Proceedings of the 22nd international conference on Machine learning
Discriminative learning of beam-search heuristics for planning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Learnability of bipartite ranking functions
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Structured machine learning: the next ten years
Machine Learning
ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Empirical Assessment of Two Strategies for Optimizing the Viterbi Algorithm
AI*IA '09: Proceedings of the XIth International Conference of the Italian Association for Artificial Intelligence Reggio Emilia on Emergent Perspectives in Artificial Intelligence
Learning Linear Ranking Functions for Beam Search with Application to Planning
The Journal of Machine Learning Research
CarpeDiem: Optimizing the Viterbi Algorithm and Applications to Supervised Sequential Learning
The Journal of Machine Learning Research
Hi-index | 0.00 |
Beam search is used to maintain tractability in large search spaces at the expense of completeness and optimality. We study supervised learning of linear ranking functions for controlling beam search. The goal is to learn ranking functions that allow for beam search to perform nearly as well as unconstrained search while gaining computational efficiency. We first study the computational complexity of the learning problem, showing that even for exponentially large search spaces the general consistency problem is in NP. We also identify tractable and intractable subclasses of the learning problem. Next, we analyze the convergence of recently proposed and modified online learning algorithms. We first provide a counter-example to an existing convergence result and then introduce alternative notions of "margin" that do imply convergence. Finally, we study convergence properties for ambiguous training data.