The perceptron algorithm is fast for nonmalicious distributions
Neural Computation
A sequential algorithm for training text classifiers
SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
Selective Sampling Using the Query by Committee Algorithm
Machine Learning
On PAC learning using Winnow, Perceptron, and a Perceptron-like algorithm
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Query by committee, linear separation and random walks
Theoretical Computer Science
ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
A polynomial-time algorithm for learning noisy linear threshold functions
FOCS '96 Proceedings of the 37th Annual Symposium on Foundations of Computer Science
Information Processing Letters
Worst-Case Analysis of Selective Sampling for Linear Classification
The Journal of Machine Learning Research
On the sample complexity of PAC learning half-spaces against the uniform distribution
IEEE Transactions on Neural Networks
ICML '06 Proceedings of the 23rd international conference on Machine learning
Worst-Case Analysis of Selective Sampling for Linear Classification
The Journal of Machine Learning Research
Active sampling for multiple output identification
Machine Learning
On multi-view active learning and the combination with semi-supervised learning
Proceedings of the 25th international conference on Machine learning
Journal of Computer and System Sciences
Importance weighted active learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Robust bounds for classification via selective sampling
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Active learning with confidence
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Boosting Active Learning to Optimality: A Tractable Monte-Carlo, Billiard-Based Algorithm
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II
Minimax bounds for active learning
COLT'07 Proceedings of the 20th annual conference on Learning theory
COLT'07 Proceedings of the 20th annual conference on Learning theory
Efficiently learning mixtures of two Gaussians
Proceedings of the forty-second ACM symposium on Theory of computing
Complexity bounds for batch active learning in classification
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III
Active learning in the non-realizable case
ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory
Active sampling for multiple output identification
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Efficient algorithms for general active learning
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Rotational prior knowledge for SVMs
ECML'05 Proceedings of the 16th European conference on Machine Learning
Activized learning: transforming passive to active with improved label complexity
The Journal of Machine Learning Research
Selective sampling and active learning from single and multiple teachers
The Journal of Machine Learning Research
Efficient active learning of halfspaces: an aggressive approach
The Journal of Machine Learning Research
Hi-index | 0.00 |
We start by showing that in an active learning setting, the Perceptron algorithm needs $\Omega(\frac{1}{\epsilon ^{2}})$labels to learn linear separators within generalization error ε. We then present a simple selective sampling algorithm for this problem, which combines a modification of the perceptron update with an adaptive filtering rule for deciding which points to query. For data distributed uniformly over the unit sphere, we show that our algorithm reaches generalization error ε after asking for just ${\tilde O}(d log \frac{1}{\epsilon})$ labels. This exponential improvement over the usual sample complexity of supervised learning has previously been demonstrated only for the computationally more complex query-by-committee algorithm.