The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses

DOI10.1007/978-3-642-04414-4_8zbMATH Open1262.68073OpenAlexW2115393337MaRDI QIDQ3648741FDOQ3648741

Authors: Vladimir V. V'yugin 

Publication date: 1 December 2009

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-642-04414-4_8

Recommendations

• Online learning in case of unbounded losses using follow the perturbed leader algorithm
• Algorithmic Learning Theory
• Adaptive online prediction by following the perturbed leader
• Learning Theory
• Leader-following almost output consensus for linear multi-agent systems with disturbance-affected unstable zero dynamics
• scientific article; zbMATH DE number 6961442
• Algorithmic Learning Theory
• Leader-following consensus with connectivity preservation of uncertain Euler-Lagrange multi-agent systems
• Adaptive leader-following consensus for uncertain nonlinear multi-agent systems
• Leaderless adaptive output feedback consensus approach for one-sided Lipschitz multi-agents

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32)

Cites Work

• Prediction, Learning, and Games
• Title not available (Why is that?)
• The weighted majority algorithm
• Title not available (Why is that?)
• Improved second-order bounds for prediction with expert advice
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
• Algorithmic Learning Theory
• Algorithmic Learning Theory
• Efficient algorithms for online decision problems.

Cited In (6)

• Learning Volatility of Discrete Time Series Using Prediction with Expert Advice
• Adaptive online prediction by following the perturbed leader
• On minimaxity of follow the leader strategy in the stochastic setting
• Algorithmic Learning Theory
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
• Online learning in case of unbounded losses using follow the perturbed leader algorithm

This page was built for publication: The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3648741)