Exact sampling with coupled Markov chains and applications to statistical mechanics
Proceedings of the seventh international conference on Random structures and algorithms
The Markov chain Monte Carlo method: an approach to approximate counting and integration
Approximation algorithms for NP-hard problems
Exact sampling and approximate counting techniques
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
FOCS '03 Proceedings of the 44th Annual IEEE Symposium on Foundations of Computer Science
Machine Learning
Supervised clustering with support vector machines
ICML '05 Proceedings of the 22nd international conference on Machine learning
Simulated Annealing for Convex Optimization
Mathematics of Operations Research
Incremental Algorithms for Hierarchical Classification
The Journal of Machine Learning Research
Kernel-Based Learning of Hierarchical Multilabel Classification Models
The Journal of Machine Learning Research
Supervised clustering of streaming data for email batch detection
Proceedings of the 24th international conference on Machine learning
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
Proceedings of the 24th international conference on Machine learning
Logarithmic regret algorithms for online convex optimization
Machine Learning
Adaptive Simulated Annealing: A Near-optimal Connection between Sampling and Counting
FOCS '07 Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science
Proximal regularization for online and batch learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Hi-index | 0.00 |
We consider MAP estimators for structured prediction with exponential family models. In particular, we concentrate on the case that efficient algorithms for uniform sampling from the output space exist. We show that under this assumption (i) exact computation of the partition function remains a hard problem, and (ii) the partition function and the gradient of the log partition function can be approximated efficiently. Our main result is an approximation scheme for the partition function based on Markov Chain Monte Carlo theory. We also show that the efficient uniform sampling assumption holds in several application settings that are of importance in machine learning.