Add to ORKGInternational audienceIn this paper, we propose a version of the MM Subspace algorithm in a stochastic setting. We prove the convergence of the algorithm and show its good practical performances
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
International audienceThe expectation-maximization (EM) algorithm is a powerful computational techni...
International audienceIn this paper, we derive a novel MH proposal, inspired from Langevin dynamics,...
International audienceIn this paper, we propose a version of the MM Subspace algorithm in a stochast...
International audienceIn a learning context, data distribution are usually unknown. Observation mode...
International audienceStochastic optimization plays an important role in solving many problems encou...
International audienceA wide class of problems involves the minimization of a coercive and different...
International audienceState-of-the-art methods for solving smooth optimization problems are nonlinea...
We present some typical algorithms used for finding global minimum/maximum of a function defined on...
We present some typical algorithms used for finding global minimum/ maximum of a function defined on...
This thesis is about stochastic approximation analysis and application in Finance. In the first part...
Les principaux sujets étudiés dans cette thèse concernent le développement d'algorithmes stochastiqu...
IIn this paper, we extend the framework of the convergence ofstochastic approximations. Such a proce...
Learning stochastic models generating sequences has many applications in natural language processing...
The notable changes over the current version: - worked example of convergence rates showing SAG can ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
International audienceThe expectation-maximization (EM) algorithm is a powerful computational techni...
International audienceIn this paper, we derive a novel MH proposal, inspired from Langevin dynamics,...
International audienceIn this paper, we propose a version of the MM Subspace algorithm in a stochast...
International audienceIn a learning context, data distribution are usually unknown. Observation mode...
International audienceStochastic optimization plays an important role in solving many problems encou...
International audienceA wide class of problems involves the minimization of a coercive and different...
International audienceState-of-the-art methods for solving smooth optimization problems are nonlinea...
We present some typical algorithms used for finding global minimum/maximum of a function defined on...
We present some typical algorithms used for finding global minimum/ maximum of a function defined on...
This thesis is about stochastic approximation analysis and application in Finance. In the first part...
Les principaux sujets étudiés dans cette thèse concernent le développement d'algorithmes stochastiqu...
IIn this paper, we extend the framework of the convergence ofstochastic approximations. Such a proce...
Learning stochastic models generating sequences has many applications in natural language processing...
The notable changes over the current version: - worked example of convergence rates showing SAG can ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
International audienceThe expectation-maximization (EM) algorithm is a powerful computational techni...
International audienceIn this paper, we derive a novel MH proposal, inspired from Langevin dynamics,...