Λέσχη Φίλων Στατιστικής - GrStats forum
AUEB Stats Seminars 17/12/2020: Optimal data driven policies under constrained multi-armed bandit observations by Odyseas Kanavetas Forumgrstats

Join the forum, it's quick and easy

Λέσχη Φίλων Στατιστικής - GrStats forum
AUEB Stats Seminars 17/12/2020: Optimal data driven policies under constrained multi-armed bandit observations by Odyseas Kanavetas Forumgrstats
Λέσχη Φίλων Στατιστικής - GrStats forum
Would you like to react to this message? Create an account in a few clicks or log in to continue.
Για προβλήματα εγγραφής και άλλες πληροφορίες επικοινωνήστε με : grstats.forum@gmail.com ή grstats@stat-athens.aueb.gr

Go down
grstats
grstats
Posts : 931
Join date : 2009-10-21
http://stat-athens.aueb.gr/~grstats/

AUEB Stats Seminars 17/12/2020: Optimal data driven policies under constrained multi-armed bandit observations by Odyseas Kanavetas Empty AUEB Stats Seminars 17/12/2020: Optimal data driven policies under constrained multi-armed bandit observations by Odyseas Kanavetas

Tue 15 Dec 2020 - 11:26
Ημερομηνία Εκδήλωσης:
Πέμπτη, Δεκέμβριος 17, 2020 - 12:30

AUEB Stats Seminars 17/12/2020: Optimal data driven policies under constrained multi-armed bandit observations by Odyseas Kanavetas Kanave12



ΚΥΚΛΟΣ ΣΕΜΙΝΑΡΙΩΝ ΣΤΑΤΙΣΤΙΚΗΣ ΔΕΚΕΜΒΡΙΟΣ 2020

Οδυσσέας Καναβέτας, Leiden University, Mathematical Institute

Optimal data driven policies under constrained multi-armed bandit observations

Σύνδεσμος Google Meeting: meet.google.com/usq-firh-fhs

ΠΕΡΙΛΗΨΗ

After a brief review of the multi-armed bandit (MAB) problem and its online machine learning applications, we present our work on the model with side constraints. The constraints represent circumstances in which bandit activations are restricted by the availability of certain resources that are replenished at a constant rate.

We consider the class of feasible uniformly fast (f-UF) convergent policies, that satisfy sample path wise the constraints. We first establish a necessary asymptotic lower bound for the rate of increase of the regret (i.e., loss due to the need to estimate unknown parameters) function of f-UF policies. Then, under pertinent conditions, we establish the existence of asymptotically optimal policies by constructing a class of f-UF policies that achieve this lower bound.

We provide the explicit form of such policies for cases in which the unknown distributions are a) Normal with unknown means and known variances, b) Normal distributions with unknown means and unknown variances and c) arbitrary discrete distributions with finite support.
Back to top
Permissions in this forum:
You cannot reply to topics in this forum