On the Generalization Ability of On-Line Learning Algorithms

DOI10.1109/TIT.2004.833339zbMath1295.68182WikidataQ59538600 ScholiaQ59538600MaRDI QIDQ3546662

Nicolò Cesa-Bianchi, Claudio Gentile, Alex Conconi

Publication date: 21 December 2008

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Online algorithms; streaming algorithms (68W27)

Related Items (58)

Online passive-aggressive active learning ⋮ Generalization properties of doubly stochastic learning algorithms ⋮ An unbiased LSSVM model for classification and regression ⋮ Applications of regularized least squares to pattern classification ⋮ Fully online classification by regularization ⋮ Fast learning rates in statistical inference through aggregation ⋮ Online Learning with (Multiple) Kernels: A Review ⋮ Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization ⋮ Online risk-averse submodular maximization ⋮ Optimistic optimisation of composite objective with exponentiated update ⋮ No-regret dynamics in the Fenchel game: a unified framework for algorithmic convex optimization ⋮ PAMR: passive aggressive mean reversion strategy for portfolio selection ⋮ Pegasos: primal estimated sub-gradient solver for SVM ⋮ Recursive aggregation of estimators by the mirror descent algorithm with averaging ⋮ Learning Kernel Perceptrons on Noisy Data Using Random Projections ⋮ Sparse regression learning by aggregation and Langevin Monte-Carlo ⋮ Mirror averaging with sparsity priors ⋮ The asymptotics of ranking algorithms ⋮ Estimating the historical and future probabilities of large terrorist events ⋮ Discussion of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard ⋮ Rejoinder of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard ⋮ The generalization performance of ERM algorithm with strongly mixing observations ⋮ Learning to classify with missing and corrupted features ⋮ Online Pairwise Learning Algorithms ⋮ Analysis of Online Composite Mirror Descent Algorithm ⋮ Online transfer learning ⋮ Stability and optimization error of stochastic gradient descent for pairwise learning ⋮ Online minimum error entropy algorithm with unbounded sampling ⋮ Optimization Methods for Large-Scale Machine Learning ⋮ Unregularized online learning algorithms with general loss functions ⋮ Unnamed Item ⋮ A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Online chaotic time series prediction using unbiased composite kernel machine via Cholesky factorization ⋮ PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification ⋮ Unregularized online algorithms with varying Gaussians ⋮ PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification ⋮ On Martingale Extensions of Vapnik–Chervonenkis Theory with Applications to Online Learning ⋮ Online pairwise learning algorithms with convex loss functions ⋮ A primal-dual perspective of online learning algorithms ⋮ Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity ⋮ Estimating latent feature-feature interactions in large feature-rich graphs ⋮ ONLINE REGRESSION WITH VARYING GAUSSIANS AND NON-IDENTICAL DISTRIBUTIONS ⋮ Learning Hurdles for Sleeping Experts ⋮ Structural Online Learning ⋮ Making the Last Iterate of SGD Information Theoretically Optimal ⋮ Optimal Rates for Multi-pass Stochastic Gradient Methods ⋮ Unnamed Item ⋮ New insights on concentration inequalities for self-normalized martingales ⋮ Unnamed Item ⋮ Unnamed Item ⋮ On the perceptron's compression ⋮ Discussion of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard ⋮ Discussion of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard ⋮ Discussion of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard ⋮ Discussion of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard ⋮ Discussion of ``Estimating the historical and future probabilities of large terrorist events by Aaron Clauset and Ryan Woodard

This page was built for publication: On the Generalization Ability of On-Line Learning Algorithms