Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Anmol Kagrecha"'
Publikováno v:
Machine Learning. 112:431-458
We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm is determ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cbdc4c615191dd87de3cd046afa727f
https://doi.org/10.1007/s10994-022-06291-9
https://doi.org/10.1007/s10994-022-06291-9
Publikováno v:
IEEE Transactions on Information Theory. 68:5248-5267
Traditional multi-armed bandit (MAB) formulations usually make certain assumptions about the underlying arms' distributions, such as bounds on the support or their tail behaviour. Moreover, such parametric information is usually 'baked' into the algo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::555e608bec828e49b6513c2d10a0e955
https://doi.org/10.1109/tit.2022.3163524
https://doi.org/10.1109/tit.2022.3163524
Autor:
Anmol Kagrecha, Jayakrishnan Nair
Publikováno v:
COMSNETS
The performance evaluation of loss service systems, where customers who cannot be served upon arrival get dropped, has a long history going back to the classical Erlang B model. In this paper, we consider the performance benefits arising from the pos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4dd8a868aefd81e99b4ba631717ecd47
http://arxiv.org/abs/1910.12894
http://arxiv.org/abs/1910.12894
Publikováno v:
Machine Learning; Feb2023, Vol. 112 Issue 2, p431-458, 28p
Publikováno v:
IEEE Transactions on Information Theory; Aug2022, Vol. 68 Issue 8, p5248-5267, 20p