A review of uncertainty quantification in deep learning:techniques, applications and challenges

Autor: Abdar, M. (Moloud), Pourpanah, F. (Farhad), Hussain, S. (Sadiq), Rezazadegan, D. (Dana), Liu, L. (Li), Ghavamzadeh, M. (Mohammad), Fieguth, P. (Paul), Cao, X. (Xiaochun), Khosravi, A. (Abbas), Acharya, U. R. (U. Rajendra), Makarenkov, V. (Vladimir), Nahavandi, S. (Saeid)

Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of uncertainties during both optimization and decision making processes. They have been applied to solve a variety of real-world problems in science and engineering. B

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2423::9617ee124ea733924dc3b09fd6b341d8
http://urn.fi/urn:nbn:fi-fe2021090645179

Improved Learning Complexity in Combinatorial Pure Exploration Bandits

Autor: Gabillon, V., Lazaric, A., Ghavamzadeh, M., Ronald Ortner, Bartlett, P.

Publikováno v: Proceedings of the 19th International Conference on Artificial Intelligence (AISTATS)
Proceedings of the 19th International Conference on Artificial Intelligence (AISTATS), May 2016, Cadiz, Spain
Scopus-Elsevier

International audience; We study the problem of combinatorial pure exploration in the stochastic multi-armed bandit problem. We first construct a new measure of complexity that provably characterizes the learning performance of the algorithms we prop

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::370e02224efffe93bdbcfb0c94e98015
https://inria.hal.science/hal-01322198/document

Policy Gradient for Coherent Risk Measures

Autor: Tamar, A., Chow, Y., Ghavamzadeh, M., Shie Mannor

Publikováno v: Scopus-Elsevier

Several authors have recently developed risk-sensitive policy gradient methods that augment the standard expected cost minimization problem with a measure of variability in cost. These studies have focused on specific risk-measures, such as the varia

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f5f6a30d160f225eeaf60209fb78daa
http://arxiv.org/abs/1502.03919

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.