Large margin hierarchical classification
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Recursive Aggregation of Estimators by the Mirror Descent Algorithm with Averaging
Problems of Information Transmission
Noise Tolerant Variants of the Perceptron Algorithm
The Journal of Machine Learning Research
Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
Proceedings of the 24th international conference on Machine learning
Applications of regularized least squares to pattern classification
Theoretical Computer Science
Learning to classify with missing and corrupted features
Proceedings of the 25th international conference on Machine learning
The projectron: a bounded kernel-based Perceptron
Proceedings of the 25th international conference on Machine learning
Learning Kernel Perceptrons on Noisy Data Using Random Projections
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Sequence Labelling SVMs Trained in One Pass
ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
Online Manifold Regularization: A New Learning Setting and Empirical Study
ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
Discriminative keyword spotting
Speech Communication
Polyhedral outer approximations with application to natural language parsing
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Bounded Kernel-Based Online Learning
The Journal of Machine Learning Research
Online Learning with Samples Drawn from Non-identical Distributions
The Journal of Machine Learning Research
Aggregation by exponential weighting and sharp oracle inequalities
COLT'07 Proceedings of the 20th annual conference on Learning theory
Online learning with prior knowledge
COLT'07 Proceedings of the 20th annual conference on Learning theory
On complexity issues of online learning algorithms
IEEE Transactions on Information Theory
Learnability, Stability and Uniform Convergence
The Journal of Machine Learning Research
Active learning using on-line algorithms
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Double Updating Online Learning
The Journal of Machine Learning Research
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
The Journal of Machine Learning Research
Ensembles and multiple classifiers: a game-theoretic view
MCS'11 Proceedings of the 10th international conference on Multiple classifier systems
Efficient Learning with Partially Observed Attributes
The Journal of Machine Learning Research
Functional brain imaging with multi-objective multi-modal evolutionary optimization
PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature
Learning hurdles for sleeping experts
Proceedings of the 3rd Innovations in Theoretical Computer Science Conference
Competing with wild prediction rules
COLT'06 Proceedings of the 19th annual conference on Learning Theory
An online algorithm for hierarchical phoneme classification
MLMI'04 Proceedings of the First international conference on Machine Learning for Multimodal Interaction
Data dependent concentration bounds for sequential prediction algorithms
COLT'05 Proceedings of the 18th annual conference on Learning Theory
An online framework for learning novel concepts over multiple cues
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Online Learning and Online Convex Optimization
Foundations and Trends® in Machine Learning
Sparse regression learning by aggregation and Langevin Monte-Carlo
Journal of Computer and System Sciences
Sublinear optimization for machine learning
Journal of the ACM (JACM)
Confidence Weighted Mean Reversion Strategy for Online Portfolio Selection
ACM Transactions on Knowledge Discovery from Data (TKDD)
Online learning with multiple kernels: A review
Neural Computation
Cost-sensitive online active learning with application to malicious URL detection
Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Sparsity regret bounds for individual sequences in online linear regression
The Journal of Machine Learning Research
Trading regret for efficiency: online convex optimization with long term constraints
The Journal of Machine Learning Research
| Hi-index | 754.90 |
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent and identically distributed (i.i.d.) sample of data. Using a simple large deviation argument, we prove tight data-dependent bounds for the risk of this hypothesis in terms of an easily computable statistic Mn associated with the on-line performance of the ensemble. Via sharp pointwise bounds on Mn, we then obtain risk tail bounds for kernel perceptron algorithms in terms of the spectrum of the empirical kernel matrix. These bounds reveal that the linear hypotheses found via our approach achieve optimal tradeoffs between hinge loss and margin size over the class of all linear functions, an issue that was left open by previous results. A distinctive feature of our approach is that the key tools for our analysis come from the model of prediction of individual sequences; i.e., a model making no probabilistic assumptions on the source generating the data. In fact, these tools turn out to be so powerful that we only need very elementary statistical facts to obtain our final risk bounds.