Fetching the paper…
Reading the bibliography…
Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has terrible performance for worst-case data.
The weighted majority algorithm
Nick Littlestone and Manfred K. Warmuth · 1994
Earlier work this paper cites.
How to use expert advice
Nicolò Cesa-Bianchi, Yoav Freund, David Haussler, David P. Helmbold, Robert E. Schapire, and Manfred K. Warmuth · 1997
Earlier work this paper cites.
A decision-theoretic generalization of on-line learning and an application to boosting
Yoav Freund and Robert E. Schapire · 1997
Earlier work this paper cites.
A game of prediction with expert advice
Vladimir Vovk · 1998
Earlier work this paper cites.
Adaptive game playing using multiplicative weights
Yoav Freund and Robert E. Schapire · 1999
Earlier work this paper cites.
Competitive on-line statistics
Vladimir Vovk · 2001
Earlier work this paper cites.
Adaptive and self-confident on-line learning algorithms
Peter Auer, Nicolò Cesa-Bianchi, and Claudio Gentile · 2002
Earlier work this paper cites.
Efficient algorithms for online decision
Adam Kalai and Santosh Vempala · 2003
Earlier work this paper cites.
PAC-Bayesian statistical learning theory
Jean-Yves Audibert · 2004
Earlier work this paper cites.
Adaptive online prediction by following the perturbed leader
Marcus Hutter and Jan Poland · 2005
Cited alongside, same era.
The weak aggregating algorithm and weak mixability
Yuri Kalnishkan and Michael V. Vyugin · 2005
Cited alongside, same era.
Defensive forecasting
Vladimir Vovk, Akimichi Takemura, and Glenn Shafer · 2005
Cited alongside, same era.
Prediction, learning, and games
Nicolò Cesa-Bianchi and Gábor Lugosi · 2006
Cited alongside, same era.
Worst-case bounds for Gaussian process models
Sham Kakade, Matthias Seeger, and Dean Foster · 2006
Cited alongside, same era.
Information theoretical upper and lower bounds for statistical estimation
Tong Zhang · 2006
Cited alongside, same era.
Extracting certainty from uncertainty: Regret bounded by variation in costs
Elad Hazan and Satyen Kale · 2008
Later among the works it cites.
A parameter-free hedging algorithm
Kamalika Chaudhuri, Yoav Freund, and Daniel Hsu · 2009
Later among the works it cites.
Prediction with advice of unknown number of experts
Alexey V. Chernov and Vladimir Vovk · 2010
Later among the works it cites.
Prédiction de suites individuelles et cadre statistique classique: étude de quelques liens autour de la régression parcimonieuse et des techniques d’agrégation
Sébastien Gerchinovitz · 2011
Later among the works it cites.
Safe learning: bridging the gap between Bayes, MDL and statistical learning theory via empirical convexity
Peter Grünwald · 2011
Later among the works it cites.
Adaptive hedge
Tim van Erven, Peter Grünwald, Wouter M. Koolen, and Steven de Rooij · 2011
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
PAC-Bayesian Supervised Classification
Olivier Catoni · 2007
Cited alongside, same era.
Improved second-order bounds for prediction with expert advice
Nicolò Cesa-Bianchi, Yishay Mansour, and Gilles Stoltz · 2007
Cited alongside, same era.
Later among the works it cites.
Forecasting electricity consumption by aggregating specialized experts; a review of the sequential aggregation of specialized experts, with an application to Slovakian and French country-wide one-day-ahead (half -
Marie Devaine, Pierre Gaillard, Yannig Goude, and Gilles Stoltz · 2012
Later among the works it cites.
The safe Bayesian: learning the learning rate via the mixability gap
Peter Grünwald · 2012
Later among the works it cites.