Pure exploration in multi-armed bandits with low rank structure using oblivious sampler.

Yaxiong Liu Atsuyoshi Nakamura Kohei Hatano Eiji Takimoto

Published in: CoRR (2023)

Keyphrases

low rank
multi armed bandits
matrix factorization
linear combination
missing data
high dimensional data
singular value decomposition
low rank matrix
convex optimization
rank minimization
matrix completion
nearest neighbor
markov random field
markov chain
machine learning
knn
least squares
trace norm
active learning