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

by   Dirk van der Hoeven, et al.

We investigate online classification with paid stochastic experts. Here, before making their prediction, each expert must be paid. The amount that we pay each expert directly influences the accuracy of their prediction through some unknown Lipschitz "productivity" function. In each round, the learner must decide how much to pay each expert and then make a prediction. They incur a cost equal to a weighted sum of the prediction error and upfront payments for all experts. We introduce an online learning algorithm whose total cost after T rounds exceeds that of a predictor which knows the productivity of all experts in advance by at most π’ͺ(K^2(log T)√(T)) where K is the number of experts. In order to achieve this result, we combine Lipschitz bandits and online classification with surrogate losses. These tools allow us to improve upon the bound of order T^2/3 one would obtain in the standard Lipschitz bandit setting. Our algorithm is empirically evaluated on synthetic data


page 1

page 2

page 3

page 4

βˆ™ 10/27/2021

Fast rates for prediction with limited expert advice

We investigate the problem of minimizing the excess generalization error...
βˆ™ 04/12/2013

Advice-Efficient Prediction with Expert Advice

Advice-efficient prediction with expert advice (in analogy to label-effi...
βˆ™ 04/21/2022

Memory Bounds for the Experts Problem

Online learning with expert advice is a fundamental problem of sequentia...
βˆ™ 06/06/2022

A Regret-Variance Trade-Off in Online Learning

We consider prediction with expert advice for strongly convex and bounde...
βˆ™ 07/30/2009

Knowledge Elecitation for Factors Affecting Taskforce Productivity using a Questionnaire

In this paper we present the process of Knowledge Elicitation through a ...
βˆ™ 08/09/2014

Prediction with Advice of Unknown Number of Experts

In the framework of prediction with expert advice, we consider a recentl...
βˆ™ 02/27/2019

Lipschitz Adaptivity with Multiple Learning Rates in Online Learning

We aim to design adaptive online learning algorithms that take advantage...

Please sign up or login with your details

Forgot password? Click here to reset