Adaptive and sequential experiment design is a well-studied area in numerous domains. We survey and synthesize the work of the online statistical learning paradigm referred to as multi-armed bandits integrating the existing research as a resource for a certain class of online experiments. We first explore the traditional stochastic model of a multi-armed bandit, then explore a taxonomic scheme of complications to that model, for each complication relating it to a specific requirement or consideration of the experiment design context. Finally, at the end of the paper, we present a table of known bounds of regret for all studied algorithms providing both perspectives for future theoretical work and a decision-making tool for practitioners looking for theoretical guarantees. Primary 62K99, 62L05; secondary 68T05. Keywords and phrases: multi-armed bandits, adaptive experiments, sequential experiment design, online experiment design. * Loeppky and Lawrence were partly supported by Natural Sciences and Engineering Research Council of Canada Discovery Grants, grant numbers RGPIN-2015-03895 and RGPIN-341202-12 respectively. 1 imsart-generic ver. 2011/11/15 file: mab-ss-survey.tex date: November 4,

No abstract

No abstract

Web content is consumed on devices with a significant variation in display resolution. Visualizing data is typically performed by extracting data from a database for transmission to the client and then visualizing it with a client-side Javascript library. A major challenge is to retrieve only the required data for visualization. Current approaches require programmers to manually modify their data extraction queries and do not adapt to client display characteristics. The contribution in this work is a configurable data compression method that automatically adapts the amount of data transmitted for client-side visualization based on device characteristics. We evaluate several different techniques for time series summarization and show the amount of data transmitted can be reduced by between 40% and 80% on standard data sets while preserving pixel-perfect visualization.

No abstract