Follow the leader if you can, hedge if you must
From MaRDI portal
Publication:2934040
zbMATH Open1318.68162arXiv1301.0534MaRDI QIDQ2934040FDOQ2934040
Authors: Steven de Rooij, Tim van Erven, Peter D. Grünwald, Wouter M. Koolen 
Publication date: 8 December 2014
Full work available at URL: https://arxiv.org/abs/1301.0534
Recommendations
- scientific article; zbMATH DE number 7064063
- On minimaxity of follow the leader strategy in the stochastic setting
- Adaptive online prediction by following the perturbed leader
- On minimaxity of follow the leader strategy in the stochastic setting
- Online learning in case of unbounded losses using follow the perturbed leader algorithm
Cited In (15)
- Following the leader and fast rates in online linear prediction: curved constraint sets and other regularities
- Scale-free online learning
- Combining initial segments of lists
- Price probabilities: a class of Bayesian and non-Bayesian prediction rules
- Title not available (Why is that?)
- Adaptive online prediction by following the perturbed leader
- Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization
- Online algorithm for aggregating experts’ predictions with unbounded quadratic loss
- On minimaxity of follow the leader strategy in the stochastic setting
- On minimaxity of follow the leader strategy in the stochastic setting
- Hedge algorithm and dual averaging schemes
- Fast rates for general unbounded loss functions: from ERM to generalized Bayes
- Applications of combined financial strategies based on universal adaptive forecasting
- Scale-free algorithms for online linear optimization
- Online aggregation of unbounded losses using shifting experts with confidence
This page was built for publication: Follow the leader if you can, hedge if you must
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2934040)
