Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality

07/22/2012
by   Sébastien Bubeck, et al.
0

We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and on the Good-Turing missing mass estimator. We prove two different regret bounds on the performance of this algorithm under weak assumptions on the probabilistic experts. Under more restrictive hypotheses, we also prove a macroscopic optimality result, comparing the algorithm both with an oracle strategy and with uniform sampling. Finally, we provide numerical experiments illustrating these theoretical findings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/27/2019

Adaptive Hedging under Delayed Feedback

The article is devoted to investigating the application of hedging strat...
research
06/25/2018

On consistent estimation of the missing mass

Given n samples from a population of individuals belonging to different ...
research
02/06/2019

On the asymptotic optimality of the comb strategy for prediction with expert advice

For the problem of prediction with expert advice in the adversarial sett...
research
12/03/2019

Experimental Evidence for Asymptotic Non-Optimality of Comb Adversary Strategy

For the problem of prediction with expert advice in the adversarial sett...
research
07/07/2021

Episodic Bandits with Stochastic Experts

We study a version of the contextual bandit problem where an agent is gi...
research
08/14/2018

Adaptive Sampling for Convex Regression

In this paper, we introduce the first principled adaptive-sampling proce...
research
03/27/2013

A Framework for Non-Monotonic Reasoning About Probabilistic Assumptions

Attempts to replicate probabilistic reasoning in expert systems have typ...

Please sign up or login with your details

Forgot password? Click here to reset