4 papers
An hybrid stochastic Newton algorithm for logistic regression
Bernard Bercu, Luis Fredes, Eméric Gbaguidi
In this paper, we investigate a second-order stochastic algorithm for solving large-scale binary classification problems. We propose to make use of a new hybrid stochastic Newton a…
On the SAGA algorithm with decreasing step
Luis Fredes, Bernard Bercu, Eméric Gbaguidi
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 Acceler…
Sharp Large Deviations for the Number of Descents and the Major Index in a Random Permutation
Bernard Bercu, Michel Bonnefont, Luis Fredes +1
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.…
Sharp analysis on the joint distribution of the number of descents and inverse descents in a random permutation
Luis Fredes, Bernard Bercu, Michel Bonnefont +1
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 noteworth…