Machine Learning - Special issue on inductive transfer
A polynomial-time approximation algorithm for the permanent of a matrix with non-negative entries
STOC '01 Proceedings of the thirty-third annual ACM symposium on Theory of computing
Tracking a small set of experts by mixing past posteriors
The Journal of Machine Learning Research
Learning Multiple Tasks with Kernel Methods
The Journal of Machine Learning Research
Efficient algorithms for online decision problems
Journal of Computer and System Sciences - Special issue: Learning theory 2003
Prediction, Learning, and Games
Prediction, Learning, and Games
A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data
The Journal of Machine Learning Research
A model of inductive bias learning
Journal of Artificial Intelligence Research
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Online discovery of similarity mappings
Proceedings of the 24th international conference on Machine learning
N-best reranking by multitask learning
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
SODA '10 Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms
Linear Algorithms for Online Multitask Classification
The Journal of Machine Learning Research
Online multiple tasks one-shot learning of object categories and vision
Proceedings of the 9th International Conference on Advances in Mobile Computing and Multimedia
Fast multi-task learning for query spelling correction
Proceedings of the 21st ACM international conference on Information and knowledge management
Hi-index | 0.00 |
We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the "ideal" algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques.