Motivated by A/B/n testing applications, we consider a finite set of
dis...
Suppose we observe an infinite series of coin flips X_1,X_2,…, and wish
...
Wald's anytime-valid p-values and Robbins' confidence sequences enable
s...
We present a new theory of hypothesis testing. The main concept is the
S...
This paper presents new deviation inequalities that are valid uniformly ...
Learning the minimum/maximum mean among a finite set of distributions is...
Recent advances in bandit tools and techniques for sequential learning a...
We study an original problem of pure exploration in a strategic bandit m...