Results 21 to 30 of about 31,101 (332)
Concentration inequalities for upper probabilities
Journal of Inequalities and Applications, 2020 In this paper, we obtain a Bernstein-type concentration inequality and McDiarmid’s inequality under upper probabilities for exponential independent random variables.
Yuzhen Tan
doaj +1 more source
Convergence of Measures on Non-Archimedean Hybrid Spaces [PDF]
, 2023 We study the convergence of certain classes of complex geometric measures to certain non-Archimedean measures. This convergence takes place on the non-Archimedean hybrid space introduced by Boucksom and Jonsson.
Shivaprasad, Sanal
core +1 more source
Accelerating optimization over the space of probability measures [PDF]
Journal of machine learning research, 2023 The acceleration of gradient-based optimization methods is a subject of significant practical and theoretical importance, particularly within machine learning applications. While much attention has been directed towards optimizing within Euclidean space,
Shi Chen +3 more
semanticscholar +1 more source
Développement Durable et Territoires, 2023 The vegetated spaces located around Western cities (agricultural land, wooded areas, wetlands, abandoned spaces or recreated nature), are now integrated into metropolitan policies for the management and preservation of nature and landscapes.
Fabien Roussel
doaj +1 more source
Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM [PDF]
Neural Information Processing Systems, 2022 Many problems in machine learning can be formulated as optimizing a convex functional over a vector space of measures. This paper studies the convergence of the mirror descent algorithm in this infinite-dimensional setting.
Pierre-Cyril Aubin-Frankowski +2 more
semanticscholar +1 more source
Symmetric Spaces of Measurable Functions: Old and New Advances
Современная математика: Фундаментальные направления, 2020 The article is an extensive review in the theory of symmetric spaces of measurable functions. It contains a number of new (recent) and old (known) results in this field.
M. A. Muratov, B.-Z. A. Rubshtein
doaj +1 more source
Convergence of probability measures and Markov decision models with incomplete information [PDF]
Proceedings of the Steklov Institute of Mathematics, 2014 This paper deals with three major types of convergence of probability measures on metric spaces: weak convergence, setwise convergence, and convergence in total variation.
E. Feinberg, P. Kasyanov, M. Zgurovsky
semanticscholar +1 more source
Surface measures and convergence of the Ornstein-Uhlenbeck semigroup in Wiener spaces [PDF]
, 2010 We study points of density 1/2 of sets of finite perimeter in infinite-dimensional Gaussian spaces and prove that, as in the finite-dimensional theory, the surface measure is concentrated on this class of points.
L. Ambrosio, A. Figalli
semanticscholar +1 more source
A large deviation principle for empirical measures on Polish spaces: Application to singular Gibbs measures on manifolds [PDF]
Annales De L Institut Henri Poincare-probabilites Et Statistiques, 2017 We prove a large deviation principle for a sequence of point processes defined by Gibbs probability measures on a Polish space. This is obtained as a consequence of a more general Laplace principle for the non-normalized Gibbs measures. We consider three
David Garc'ia-Zelada
semanticscholar +1 more source
Compact embeddings of broken Sobolev spaces and applications [PDF]
, 2009 In this paper, we present several extensions of theoretical tools for the analysis of discontinuous Galerkin (DG) method beyond the linear case.
Buffa, Annalisa, Ortner, Christoph
core +1 more source