Λέσχη Φίλων Στατιστικής - GrStats forum
AUEB Stats Seminars 17/12/2020:  Optimal data driven policies under constrained multi-armed bandit observations by Odysseas 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 Odysseas 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 : 856
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 Odysseas Kanavetas Empty AUEB Stats Seminars 17/12/2020: Optimal data driven policies under constrained multi-armed bandit observations by Odysseas Kanavetas

Wed 11 Nov 2020 - 14:46
ΚΥΚΛΟΣ ΣΕΜΙΝΑΡΙΩΝ ΣΤΑΤΙΣΤΙΚΗΣ ΔΕΚΕΜΒΡΙΟΣ 2020

AUEB Stats Seminars 17/12/2020:  Optimal data driven policies under constrained multi-armed bandit observations by Odysseas Kanavetas Kanave10


Odysseas Kanavetas
Leiden University, Mathematical Institute

Optimal data driven policies under constrained multi-armed bandit observations

ΠΕΜΠΤΗ 17/12/2020
12:30

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.

Fb event: https://www.facebook.com/events/669031950700971
Back to top
Permissions in this forum:
You cannot reply to topics in this forum