Batched bandit problems
نویسندگان
چکیده
منابع مشابه
Batched Bandit Problems
Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. We propose a simple policy that operates under this contraint and show that a very small number of batches gives close to minimax optimal regret bounds. As a byproduct, we derive optima...
متن کاملMaterial for : Batched Bandit Problems
Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. We propose a simple policy, and show that a very small number of batches gives close to minimax optimal regret bounds. As a byproduct, we derive optimal policies with low switching cost...
متن کاملBatched Gaussian Process Bandit Optimization via Determinantal Point Processes
Gaussian Process bandit optimization has emerged as a powerful tool for optimizing noisy black box functions. One example in machine learning is hyper-parameter optimization where each evaluation of the target function may require training a model which may involve days or even weeks of computation. Most methods for this so-called “Bayesian optimization” only allow sequential exploration of the...
متن کاملBandit Problems
We survey the literature on multi-armed bandit models and their applications in economics. The multi-armed bandit problem is a statistical decision model of an agent trying to optimize his decisions while improving his information at the same time. This classic problem has received much attention in economics as it concisely models the trade-off between exploration (trying out each arm to find ...
متن کاملGeneralized Bandit Problems
1 The questions addressed in this paper grew out of my work with Jeff Banks on bandit problems and their applications (Banks and Sundaram (1992a, 1992b, 1994)) and owe much to many discussions I had with him on this subject. I also had the benefit of several discussions with Andy McLennan, especially regarding the material in Sections 4 and 6 of this paper.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Statistics
سال: 2016
ISSN: 0090-5364
DOI: 10.1214/15-aos1381