Adaptive and self-confident on-line learning algorithms

DOI10.1006/jcss.2001.1795zbMath1006.68162OpenAlexW2055639053WikidataQ59538604 ScholiaQ59538604MaRDI QIDQ1604218

Claudio Gentile, Peter Auer, Nicolò Cesa-Bianchi

Publication date: 4 July 2002

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

Full work available at URL: https://doi.org/10.1006/jcss.2001.1795

zbMATH Keywords

linear regressionon-line learning

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (20)

Improved second-order bounds for prediction with expert advice ⋮ Adaptive and optimal online linear regression on \(\ell^1\)-balls ⋮ Stochastic optimization for real time service capacity allocation under random service demand ⋮ Forecasting electricity consumption by aggregating specialized experts ⋮ Dynamic regret of adaptive gradient methods for strongly convex problems ⋮ Scale-free online learning ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Aggregating Algorithm for a Space of Analytic Functions ⋮ A generalized online mirror descent with applications to classification and regression ⋮ Leading strategies in competitive on-line prediction ⋮ A continuous-time approach to online optimization ⋮ Sequential model aggregation for production forecasting ⋮ Internal regret in on-line portfolio selection ⋮ Internal regret in on-line portfolio selection ⋮ Competing with wild prediction rules ⋮ Regret to the best vs. regret to the average ⋮ Unnamed Item ⋮ Scale-Free Algorithms for Online Linear Optimization ⋮ Unnamed Item ⋮ Small-Loss Bounds for Online Learning with Partial Information

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An iterative row-action method for interval convex programming
• A game of prediction with expert advice
• Tracking the best disjunction
• Tracking the best expert
• The weighted majority algorithm
• On-line learning of linear functions
• Support-vector networks
• Derandomizing stochastic prediction strategies
• Analysis of two gradient-based algorithms for on-line regression
• Queries and concept learning
• 10.1162/15324430260185600
• The Perceptron: A Model for Brain Functioning. I
• How to use expert advice
• A decision-theoretic extension of stochastic complexity and its applications to learning
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Relative loss bounds for multidimensional regression problems

This page was built for publication: Adaptive and self-confident on-line learning algorithms