Prediction with Advice of Unknown Number of Experts

08/09/2014
by   Alexey Chernov, et al.
0

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/14/2023

Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice

We investigate the problem of bandits with expert advice when the expert...
research
08/31/2017

Efficient tracking of a growing number of experts

We consider a variation on the problem of prediction with expert advice,...
research
11/15/2022

Weighting Experts with Inaccurate Judges

We consider the problem of aggregating binary votes from an ensemble of ...
research
11/08/2017

Long-Term Sequential Prediction Using Expert Advice

For the prediction with expert advice setting, we consider methods to co...
research
02/23/2018

Contextual Bandits with Stochastic Experts

We consider the problem of contextual bandits with stochastic experts, w...
research
05/24/2023

No-Regret Online Prediction with Strategic Experts

We study a generalization of the online binary prediction with expert ad...
research
07/03/2023

Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts

We investigate online classification with paid stochastic experts. Here,...

Please sign up or login with your details

Forgot password? Click here to reset