Zobrazeno 1 - 10
of 240
pro vyhledávání: '"Bercu, Bernard"'
Stochastic optimization naturally appear in many application areas, including machine learning. Our goal is to go further in the analysis of the Stochastic Average Gradient Accelerated (SAGA) algorithm. To achieve this, we introduce a new $\lambda$-S
Externí odkaz:
http://arxiv.org/abs/2410.03760
The aim of this paper is to improve the large deviation principle for the number of descents in a random permutation by establishing a sharp large deviation principle of any order. We shall also prove a sharp large deviation principle of any order fo
Externí odkaz:
http://arxiv.org/abs/2407.05708
Tools from optimal transport (OT) theory have recently been used to define a notion of quantile function for directional data. In practice, regularization is mandatory for applications that require out-of-sample estimates. To this end, we introduce a
Externí odkaz:
http://arxiv.org/abs/2407.02085
Chatteerjee and Diaconis have recently shown the asymptotic normality for the joint distribution of the number of descents and inverse descents in a random permutation. A noteworthy point of their results is that the asymptotic variance of the normal
Externí odkaz:
http://arxiv.org/abs/2405.13439
A martingale approach to Gaussian fluctuations and laws of iterated logarithm for Ewens-Pitman model
Autor:
Bercu, Bernard, Favaro, Stefano
The Ewens-Pitman model refers to a distribution for random partitions of $[n]=\{1,\ldots,n\}$, which is indexed by a pair of parameters $\alpha \in [0,1)$ and $\theta>-\alpha$, with $\alpha=0$ corresponding to the Ewens model in population genetics.
Externí odkaz:
http://arxiv.org/abs/2404.07694
We propose center-outward superquantile and expected shortfall functions, with applications to multivariate risk measurements, extending the standard notion of value at risk and conditional value at risk from the real line to $\mathbb{R}^d$. Our new
Externí odkaz:
http://arxiv.org/abs/2307.01584
We introduce a new stochastic algorithm for solving entropic optimal transport (EOT) between two absolutely continuous probability measures $\mu$ and $\nu$. Our work is motivated by the specific setting of Monge-Kantorovich quantiles where the source
Externí odkaz:
http://arxiv.org/abs/2302.00982
The goal of this paper is to go further in the analysis of the behavior of the number of descents in a random permutation. Via two different approaches relying on a suitable martingale decomposition or on the Irwin-Hall distribution, we prove that th
Externí odkaz:
http://arxiv.org/abs/2210.10382
Autor:
Bercu, Bernard
The aim of this paper is to investigate the asymptotic behavior of the so-called elephant random walk with stops (ERWS). In contrast with the standard elephant random walk, the elephant is allowed to be lazy by staying on his own position. We prove t
Externí odkaz:
http://arxiv.org/abs/2203.04196