Improved bounds on the sample complexity of learning

From MaRDI portal
Publication:5943102

DOI10.1006/jcss.2000.1741zbMath0990.68081OpenAlexW1991417304MaRDI QIDQ5943102

Aravind Srinivasan, Yi Li, Philip M. Long

Publication date: 9 September 2001

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.2000.1741




Related Items (32)

Optimal approximations made easyUnnamed ItemSubmodular Functions: Learnability, Structure, and OptimizationThe \(\varepsilon\)-\(t\)-net problemJourney to the Center of the Point SetThe VC dimension of metric balls under Fréchet and Hausdorff distancesShallow packings, semialgebraic set systems, macbeath regions, and polynomial partitioningNear-optimal coresets of kernel density estimatesEstimating the clustering coefficient using sample complexity analysisRange minima queries with respect to a random permutation, and approximate range countingRelative \((p,\varepsilon )\)-approximations in geometryShape matching under rigid motionUnnamed ItemDynamic planar Voronoi diagrams for general distance functions and their algorithmic applicationsCore-Sets: Updated SurveyTurning Big Data Into Tiny Data: Constant-Size Coresets for $k$-Means, PCA, and Projective ClusteringFast approximation of betweenness centrality through samplingA Size-Sensitive Discrepancy Bound for Set Systems of Bounded Primal Shatter DimensionUnnamed ItemUnnamed ItemUnnamed ItemSampling-based algorithm for link prediction in temporal networksTwo proofs for shallow packingsLearning big (image) data via coresets for dictionariesTheory of Classification: a Survey of Some Recent AdvancesOn coresets for support vector machinesGreedy Strategy Works for k-Center Clustering with Outliers and Coreset ConstructionUnnamed ItemThe Communication Complexity of Distributed epsilon-ApproximationsSubsampling in Smoothed Range SpacesSafe Multi-Agent Pathfinding with Time UncertaintyUnnamed Item



Cites Work


This page was built for publication: Improved bounds on the sample complexity of learning