3 papers
stat.ML2024
Unified theory of upper confidence bound policies for bandit problems targeting total reward, maximal reward, and more
Nobuaki Kikkawa, Hiroshi Ohno
The upper confidence bound (UCB) policy is recognized as an order-optimal solution for the classical total-reward bandit problem. While similar UCB-based approaches have been appli…
cond-mat.mes-hall2023
Accurate multiscale simulation of frictional interfaces by Quantum Mechanics/Green's Function molecular dynamics
Seiji Kajita, Alberto Pacini, Gabriele Losi +2
Understanding frictional phenomena is a fascinating fundamental problem with huge potential impact on energy saving. Such an understanding requires monitoring what happens at the s…
stat.ML2022
Materials Discovery using Max K-Armed Bandit
Nobuaki Kikkawa, Hiroshi Ohno
Search algorithms for the bandit problems are applicable in materials discovery. However, the objectives of the conventional bandit problem are different from those of materials di…