On the complexity of learning from drifting distributions

DOI10.1006/INCO.1997.2656MaRDI QIDQ1376422zbMATH OpenOpenAlexFDO

Authors Rakesh D. Barve, Philip M. Long

Publication date 25 May 1998

Published in Information and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1006/inco.1997.2656

zbMATH Keywords

on-line learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• The complexity of learning according to two models of a drifting environment
• New analysis and algorithm for learning with drifting distributions
• Learning with a drifting target concept
• Learning changing concepts by exploiting the structure of change
• Advances in Artificial Intelligence – SBIA 2004

Cites work

• scientific article; zbMATH DE number 53984 (Why is no real title available?)
• scientific article; zbMATH DE number 67626 (Why is no real title available?)
• scientific article; zbMATH DE number 1306864 (Why is no real title available?)
• scientific article; zbMATH DE number 3436645 (Why is no real title available?)
• scientific article; zbMATH DE number 3195517 (Why is no real title available?)
• A general lower bound on the number of examples needed for learning
• A theory of the learnable
• Convergence of stochastic processes
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Learnability and the Vapnik-Chervonenkis dimension
• Learning changing concepts by exploiting the structure of change
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• On the density of families of sets
• Predicting \(\{ 0,1\}\)-functions on randomly drawn points
• Prediction, learning, uniform convergence, and scale-sensitive dimensions
• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• Probably Approximate Learning of Sets and Functions
• Sharper bounds for Gaussian and empirical processes
• The hardness of approximate optima in lattices, codes, and systems of linear equations
• The weighted majority algorithm
• Tracking drifting concepts by minimizing disagreements
• Tracking the best expert

Cited in

(12)

• Learning from non-iid data: fast rates for the one-vs-all multiclass plug-in classifiers
• The complexity of learning according to two models of a drifting environment
• Learning changing concepts by exploiting the structure of change
• Learning distributions by their density levels: A paradigm for learning without a teacher
• New analysis and algorithm for learning with drifting distributions
• Learning with a drifting target concept
• Generalization bounds for non-stationary mixing processes
• Discrepancy-based theory and algorithms for forecasting non-stationary time series
• Improved lower bounds for learning from noisy examples: An information-theoretic approach
• Statistical mechanics of online learning of drifting concepts: A variational approach
• A no-free-lunch theorem for multitask learning
• Advances in Artificial Intelligence – SBIA 2004

This page was built for publication: On the complexity of learning from drifting distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1376422)