Open problem: Shifting experts on easy data

Warmuth, Manfred K. & Koolen, Wouter M. (2014) Open problem: Shifting experts on easy data. In Szepesvári, Csaba & Balcan, Maria-Florina (Eds.) The 27th Annual Conference on Learning Theory (COLT 2014), 13-15 June 2014, Barcelona, Spain.

View at publisher (open access)

Abstract

A number of online algorithms have been developed that have small additional loss (regret) compared to the best “shifting expert”. In this model, there is a set of experts and the comparator is the best partition of the trial sequence into a small number of segments, where the expert of smallest loss is chosen in each segment. The regret is typically defined for worst-case data / loss sequences.

There has been a recent surge of interest in online algorithms that combine good worst-case guarantees with much improved performance on easy data. A practically relevant class of easy data is the case when the loss of each expert is iid and the best and second best experts have a gap between their mean loss. In the full information setting, the FlipFlop algorithm by De Rooij et al. (2014) combines the best of the iid optimal Follow-The-Leader (FL) and the worst-case-safe Hedge algorithms, whereas in the bandit information case SAO by Bubeck and Slivkins (2012) competes with the iid optimal UCB and the worst-case-safe EXP3.

We ask the same question for the shifting expert problem. First, we ask what are the simple and efficient algorithms for the shifting experts problem when the loss sequence in each segment is iid with respect to a fixed but unknown distribution. Second, we ask how to efficiently unite the performance of such algorithms on easy data with worst-case robustness.

A particular intriguing open problem is the case when the comparator shifts within a small subset of experts from a large set under the assumption that the losses in each segment are iid.

Impact and interest:

0 citations in Scopus
Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

20 since deposited on 12 Mar 2015
7 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 82488
Item Type: Conference Item (Other)
Refereed: No
Additional Information: JMLR W&CP 35 :1295-1298, 2014
ISSN: 1533-7928
Divisions: Current > QUT Faculties and Divisions > Science & Engineering Faculty
Past > Schools > Mathematical Sciences
Copyright Owner: Copyright 2014 M.K. Warmuth & W.M. Koolen
Deposited On: 12 Mar 2015 22:59
Last Modified: 26 May 2015 22:05

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page