On the complexity of learning from drifting distributions

DOI10.1006/INCO.1997.2656zbMATH Open0887.68093OpenAlexW2092714606MaRDI QIDQ1376422FDOQ1376422

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

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

zbMATH Keywords

on-line learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• Convergence of stochastic processes
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• On the density of families of sets
• Sharper bounds for Gaussian and empirical processes
• Title not available (Why is that?)
• Learnability and the Vapnik-Chervonenkis dimension
• The weighted majority algorithm
• A theory of the learnable
• Tracking the best expert
• A general lower bound on the number of examples needed for learning
• Probably Approximate Learning of Sets and Functions
• The hardness of approximate optima in lattices, codes, and systems of linear equations
• Title not available (Why is that?)
• Title not available (Why is that?)
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Tracking drifting concepts by minimizing disagreements
• Predicting \(\{ 0,1\}\)-functions on randomly drawn points
• Prediction, learning, uniform convergence, and scale-sensitive dimensions
• Title not available (Why is that?)
• Title not available (Why is that?)
• Learning changing concepts by exploiting the structure of change

Cited In (11)

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

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)