Zobrazeno 1 - 10
of 75
pro vyhledávání: '"Approximation stochastique"'
Autor:
Rankawat, Anushree
L'idée centrale de cette thèse est de comprendre la notion d'accélération dans les algorithmes d'approximation stochastique. Plus précisément, nous tentons de répondre à la question suivante : Comment l'accélération apparaît-elle naturelle
Autor:
Kamalov, Mikhail
Publikováno v:
Artificial Intelligence [cs.AI]. Université Côte d'Azur, 2022. English. ⟨NNT : 2022COAZ4079⟩
Nowadays, graph-based semi-supervised learning (GB-SSL) is a fast-growing area of classifying nodes in a graph with an extremely low number of labelled nodes. However, the GB-SSL algorithms have two general limitations: the first is the memory/time c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::e2fbc41a90b66fe7361b48636605f659
https://theses.hal.science/tel-04042245/document
https://theses.hal.science/tel-04042245/document
Autor:
Barakat, Anas
Publikováno v:
Machine Learning [stat.ML]. Institut Polytechnique de Paris, 2021. English. ⟨NNT : 2021IPPAT030⟩
This thesis is focused on the convergence analysis of some popular stochastic approximation methods in use in the machine learning community with applications to optimization and reinforcement learning.The first part of the thesis is devoted to a pop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::235f03ef23c97b83c7cd1882980f2ff7
https://tel.archives-ouvertes.fr/tel-03485159
https://tel.archives-ouvertes.fr/tel-03485159
Autor:
Ben Khadher, Fatma
Publikováno v:
Mathematics [math]. Université de Monastir, Faculté des Sciences de Monastir-Tunisie, 2021. English
The main objective of this thesis resides in applying the stochastic approximation method to build up a large class of recursive non parametric kernel estimators for dependent and independent variables. First, we define a recursive kernel estimator o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2592::060297bb1b1353388ae7bc68ef72c93f
https://hal.archives-ouvertes.fr/tel-03514636
https://hal.archives-ouvertes.fr/tel-03514636
Autor:
Martel, Yannick
L’algorithme EM (Dempster et al., 1977) permet de construire une séquence d’estimateurs qui converge vers l’estimateur de vraisemblance maximale pour des modèles à données manquantes pour lesquels l’estimateur du maximum de vraisemblance
Externí odkaz:
http://hdl.handle.net/1866/25477
Autor:
Vo, Thi Phuong Thuy
Publikováno v:
Mathematics [math]. Université Sorbonne Paris Nord, 2020. English
The study of Respondent Driven Sampling (RDS) is invested for the discovery of a social network of hidden populations. It leads to the study of a Markov chain on a random graph whose vertices represent individuals and whose edges describe the relatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______212::438380a54a9038b242bf26a1146f2f34
https://tel.archives-ouvertes.fr/tel-03104255/file/main.pdf
https://tel.archives-ouvertes.fr/tel-03104255/file/main.pdf
Autor:
Vo, Thi Phuong Thuy
Publikováno v:
Mathematics [math]. Université Sorbonne Paris Nord, 2020. English
The study of Respondent Driven Sampling (RDS) is invested for the discovery of a social network of hidden populations. It leads to the study of a Markov chain on a random graph whose vertices represent individuals and whose edges describe the relatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2592::438380a54a9038b242bf26a1146f2f34
https://tel.archives-ouvertes.fr/tel-03104255/file/main.pdf
https://tel.archives-ouvertes.fr/tel-03104255/file/main.pdf
Autor:
Pillaud-Vivien, Loucas
Publikováno v:
Machine Learning [stat.ML]. Paris, Science et Lettres; Inria de Paris; Ecole Normale Supérieure, 2020. English
Machine Learning has received a lot of attention during the last two decades both from industry for data-driven decision problems and from the scientific community in general. This recent attention is certainly due to its ability to efficiently solve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______212::682555e6e3c084687a13b4b58fffb00b
https://hal.inria.fr/tel-03162165/document
https://hal.inria.fr/tel-03162165/document
Autor:
Oodally, Ajmal
Publikováno v:
Méthodologie [stat.ME]. Université Paris-Saclay, 2020. Français. ⟨NNT : 2020UPASM003⟩
This thesis deals with estimation in frailty models in survival analysis. Our first contribution concerns a new estimation method based on integrated partial likelihood in the frailty model. No approximation of the integrated partial likelihood is ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2592::6670490b04732fe9639b9d16103c406e
https://tel.archives-ouvertes.fr/tel-03112234/file/95362_OODALLY_2020_archivage.pdf
https://tel.archives-ouvertes.fr/tel-03112234/file/95362_OODALLY_2020_archivage.pdf
Publikováno v:
52e Journées de Statistique
52e Journées de Statistique, Société Française de Statistique, Jul 2020, Nice, France
HAL
52e Journées de Statistique, Société Française de Statistique, Jul 2020, Nice, France
HAL
In an online setting, where data arrives continuously, we want to update the parameters of a "batch" score constructed with an ensemble method. To do so, we use stochastic approximation processes, the convergence of which has been theoretically estab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8ff51140db3dd1664c04130d273f5c79
https://hal.archives-ouvertes.fr/hal-02894908/document
https://hal.archives-ouvertes.fr/hal-02894908/document