Improved Risk Tail Bounds for On-Line Algorithms

DOI10.1109/TIT.2007.911292MaRDI QIDQ3604417zbMATH OpenDBLPWikidataFDO

Authors Nicolò Cesa-Bianchi, Claudio Gentile

Publication date 24 February 2009

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

Full work available at URL https://doi.org/10.1109/TIT.2007.911292

zbMATH Keywords

Martingaleson-line learningrisk boundsstatistical learning theory

Mathematics Subject Classification ID

Approximations to statistical distributions (nonasymptotic) (62E17) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Recommendations

• On the Generalization Ability of On-Line Learning Algorithms
• Relative expected instantaneous loss bounds
• A Randomized Online Learning Algorithm for Better Variance Control
• Risk bounds for statistical learning
• Learning Theory

Cited in

(7)

• New insights on concentration inequalities for self-normalized martingales
• Online regularized learning with pairwise loss functions
• On the Generalization Ability of On-Line Learning Algorithms
• Real-time model learning using incremental sparse spectrum Gaussian process regression
• Optimistic optimisation of composite objective with exponentiated update
• Convergence rate analysis for optimal computing budget allocation algorithms
• Forecasting the cost of drought events in France by super learning from a short time series of many slightly dependent data

This page was built for publication: Improved Risk Tail Bounds for On-Line Algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3604417)