We investigate the fixed-budget best-arm identification (BAI) problem fo...
Adaptive experimental design methods are increasingly being used in indu...
In the stochastic contextual bandit setting, regret-minimizing algorithm...
Active learning methods have shown great promise in reducing the number ...
In this work we consider the problem of regret minimization for logistic...
The level set estimation problem seeks to find all points in a domain X ...
This work considers the problem of selective-sampling for best-arm
ident...
We consider active learning for binary classification in the agnostic
po...
We propose improved fixed-design confidence bounds for the linear logist...
In many scientific settings there is a need for adaptive experimental de...
Given a number of pairwise preferences of items, a common task is to ran...
This paper proposes near-optimal algorithms for the pure-exploration lin...
The pure-exploration problem in stochastic multi-armed bandits aims to f...
In this paper we introduce the transductive linear bandit problem: given...
We prove optimal bounds for the convergence rate of ordinal embedding (a...
We propose an adaptive sampling approach for multiple testing which aims...
We consider the problem of active coarse ranking, where the goal is to s...
Many modern data-intensive computational problems either require, or ben...
This paper investigates the theoretical foundations of metric learning,
...
The goal of ordinal embedding is to represent items as points in a
low-d...