Bernard Bercu

activity

20242026

collaborators

5 papers

math.PR2026

A Central Limit Theorem for the Ewens-Pitman random partition in the large- $θ$ regime via a martingale approach

Bernard Bercu, Claudia Contardi, Emanuele Dolera +1

The Ewens-Pitman model defines a distribution on random partitions of ${1, \dots, n}$ , with parameters $α \in [0, 1)$ and $θ > - α$ ; the case $α = 0$ reduces to the classical Ewens mode…

math.PR2026

A Gaussian process limit for the self-normalized Ewens-Pitman process

Bernard Bercu, Stefano Favaro

For an integer $n \geq 1$ , consider a random partition $Π_{n}$ of ${1, \dots, n}$ into $K_{n}$ partition sets with $K_{r, n}$ partition subsets of size $r = 1, \dots, n$ , and assume $Π_…

stat.CO2025

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…

math.PR2025

A new look on large deviations and concentration inequalities for the Ewens-Pitman model

Bernard Bercu, Stefano Favaro

The Ewens-Pitman model is a probability distribution for random partitions of the set $[n] = {1, \dots, n}$ , parameterized by $α \in [0, 1)$ and $θ > - α$ , with $α = 0$ corresponding to the…

math.OC2024

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…