Zobrazeno 1 - 10
of 683
pro vyhledávání: '"A. Lavenant"'
The Gibbs sampler (a.k.a. Glauber dynamics and heat-bath algorithm) is a popular Markov Chain Monte Carlo algorithm which iteratively samples from the conditional distributions of a probability measure $\pi$ of interest. Under the assumption that $\p
Externí odkaz:
http://arxiv.org/abs/2410.00858
Autor:
Lavenant, Hugo, Zanella, Giacomo
The Coordinate Ascent Variational Inference scheme is a popular algorithm used to compute the mean-field approximation of a probability distribution of interest. We analyze its random scan version, under log-concavity assumptions on the target densit
Externí odkaz:
http://arxiv.org/abs/2406.07292
We propose a new metric between probability measures on a compact metric space that mirrors the Riemannian manifold-like structure of quadratic optimal transport but includes entropic regularization. Its metric tensor is given by the Hessian of the S
Externí odkaz:
http://arxiv.org/abs/2405.04987
Autor:
Catalano, Marta, Lavenant, Hugo
Random probabilities are a key component to many nonparametric methods in Statistics and Machine Learning. To quantify comparisons between different laws of random probabilities several works are starting to use the elegant Wasserstein over Wasserste
Externí odkaz:
http://arxiv.org/abs/2402.00423
Quantitative convergence of a discretization of dynamic optimal transport using the dual formulation
Autor:
Ishida, Sadashige, Lavenant, Hugo
We present a discretization of the dynamic optimal transport problem for which we can obtain the convergence rate for the value of the transport cost to its continuous value when the temporal and spatial stepsize vanish. This convergence result does
Externí odkaz:
http://arxiv.org/abs/2312.12213
Autor:
Lavenant, Hugo
How can one lift a functional defined on maps from a space X to a space Y into a functional defined on maps from X into P(Y) the space of probability distributions over Y? Looking at measure-valued maps can be interpreted as knowing a classical map w
Externí odkaz:
http://arxiv.org/abs/2309.02260
Autor:
Catalano, Marta, Lavenant, Hugo
The Dirichlet process has been pivotal to the development of Bayesian nonparametrics, allowing one to learn the law of the observations through closed-form expressions. Still, its learning mechanism is often too simplistic and many generalizations ha
Externí odkaz:
http://arxiv.org/abs/2305.06116
Autor:
Kendra L. Ratnapradipa, Runqiu Wang, Josiane Kabayundo, Walter Marquez Lavenant, Eleanore Nelson, Muskan Ahuja, Ying Zhang, Hongmei Wang
Publikováno v:
BMC Health Services Research, Vol 24, Iss 1, Pp 1-10 (2024)
Abstract Background Healthcare accessibility and utilization are important social determinants of health. Lack of access to healthcare, including missed or no-show appointments, can have negative health effects and be costly to patients and providers
Externí odkaz:
https://doaj.org/article/9878ab4ee3ef4f7bb9f4653ce950890f
Publikováno v:
Journal of Neurogastroenterology & Motility. Oct2024, Vol. 30 Issue 4, p421-429. 9p.
Autor:
Baradat, Aymeric, Lavenant, Hugo
We consider the problem of minimizing the entropy of a law with respect to the law of a reference branching Brownian motion under density constraints at an initial and final time. We call this problem the branching Schr\"odinger problem by analogy wi
Externí odkaz:
http://arxiv.org/abs/2111.01666