Decision theoretic generalizations of the PAC model for neural net and other learning applications
Information and Computation
Improving Generalization with Active Learning
Machine Learning - Special issue on structured connectionist systems
Learning with restricted focus of attention
Journal of Computer and System Sciences
The Nonstochastic Multiarmed Bandit Problem
SIAM Journal on Computing
Learning cost-sensitive active classifiers
Artificial Intelligence
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Prediction, Learning, and Games
Prediction, Learning, and Games
ICML '06 Proceedings of the 23rd international conference on Machine learning
Approximation algorithms for budgeted learning problems
Proceedings of the thirty-ninth annual ACM symposium on Theory of computing
A bound on the label complexity of agnostic active learning
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
Efficient projections onto the l1-ball for learning in high dimensions
Proceedings of the 25th international conference on Machine learning
Bandit-Based Algorithms for Budgeted Learning
ICDM '07 Proceedings of the 2007 Seventh IEEE International Conference on Data Mining
Importance weighted active learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Compressed and privacy-sensitive sparse regression
IEEE Transactions on Information Theory
Differential privacy: a survey of results
TAMC'08 Proceedings of the 5th international conference on Theory and applications of models of computation
Logarithmic regret algorithms for online convex optimization
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Learning and classifying under hard budgets
ECML'05 Proceedings of the 16th European conference on Machine Learning
On the generalization ability of on-line learning algorithms
IEEE Transactions on Information Theory
Besting the quiz master: crowdsourcing incremental classification games
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Multi-label learning under feature extraction budgets
Pattern Recognition Letters
Hi-index | 0.00 |
We investigate three variants of budgeted learning, a setting in which the learner is allowed to access a limited number of attributes from training or test examples. In the "local budget" setting, where a constraint is imposed on the number of available attributes per training example, we design and analyze an efficient algorithm for learning linear predictors that actively samples the attributes of each training instance. Our analysis bounds the number of additional examples sufficient to compensate for the lack of full information on the training set. This result is complemented by a general lower bound for the easier "global budget" setting, where it is only the overall number of accessible training attributes that is being constrained. In the third, "prediction on a budget" setting, when the constraint is on the number of available attributes per test example, we show that there are cases in which there exists a linear predictor with zero error but it is statistically impossible to achieve arbitrary accuracy without full information on test examples. Finally, we run simple experiments on a digit recognition problem that reveal that our algorithm has a good performance against both partial information and full information baselines.