Fast rates for prediction with limited expert advice - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Fast rates for prediction with limited expert advice


We investigate the problem of minimizing the excess generalization error with respect to the best expert prediction in a finite family in the stochastic setting, under limited access to information. We assume that the learner only has access to a limited number of expert advices per training round, as well as for prediction. Assuming that the loss function is Lipschitz and strongly convex, we show that if we are allowed to see the advice of only one expert per round for T rounds in the training phase, or to use the advice of only one expert for prediction in the test phase, the worst-case excess risk is Ω(1/ √ T) with probability lower bounded by a constant. However, if we are allowed to see at least two actively chosen expert advices per training round and use at least two experts for prediction, the fast rate O(1/T) can be achieved. We design novel algorithms achieving this rate in this setting, and in the setting where the learner has a budget constraint on the total number of observed expert advices, and give precise instance-dependent bounds on the number of training rounds and queries needed to achieve a given generalization error precision.
Fichier principal
Vignette du fichier
NeurIPS-2021-fast-rates-for-prediction-with-limited-expert-advice-Supplemental-joined.pdf (324.76 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-03405899 , version 1 (27-10-2021)
hal-03405899 , version 2 (06-01-2022)



El Mehdi Saad, Gilles Blanchard. Fast rates for prediction with limited expert advice. NeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, [Online], United States. ⟨10.48550/arXiv.2110.14485⟩. ⟨hal-03405899v2⟩
141 View
121 Download



Gmail Mastodon Facebook X LinkedIn More