Learning The Best Expert Efficiently

11/11/2019
by   Daron Anderson, et al.
0

We consider online learning problems where the aim is to achieve regret which is efficient in the sense that it is the same order as the lowest regret amongst K experts. This is a substantially stronger requirement that achieving O(√(n)) or O(log n) regret with respect to the best expert and standard algorithms are insufficient, even in easy cases where the regrets of the available actions are very different from one another. We show that a particular lazy form of the online subgradient algorithm can be used to achieve minimal regret in a number of "easy" regimes while retaining an O(√(n)) worst-case regret guarantee. We also show that for certain classes of problem minimal regret strategies exist for some of the remaining "hard" regimes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2020

Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds

We revisit the problem of online learning with sleeping experts/bandits:...
research
03/02/2023

Improved Space Bounds for Learning with Experts

We give improved tradeoffs between space and regret for the online learn...
research
10/27/2020

Online Learning with Primary and Secondary Losses

We study the problem of online learning with primary and secondary losse...
research
04/29/2013

Optimal amortized regret in every interval

Consider the classical problem of predicting the next bit in a sequence ...
research
02/16/2023

Adaptive Selective Sampling for Online Prediction with Experts

We consider online prediction of a binary sequence with expert advice. F...
research
01/21/2019

Online Learning for Measuring Incentive Compatibility in Ad Auctions

In this paper we investigate the problem of measuring end-to-end Incenti...
research
02/22/2022

No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling

For each of T time steps, m experts report probability distributions ove...

Please sign up or login with your details

Forgot password? Click here to reset