Improved Confidence Bounds for the Linear Logistic Model
and Applications to Bandits
Kwang-Sung Jun 1 Lalit Jain 2 Blake Mason 3 Houssam Nassif 4
Abstract a feature vector for each arm. A common assumption is
that the reward is a noisy linear measurement of the under-
We propose improved fixed-design confidence lying feature vector of the arm being pulled. In other words,
bounds for the lin ...


雷达卡




京公网安备 11010802022788号







