output
20072025
most citedDeep Learning for Procedural Content Generation

143 citations

22 papers

math.PR2025

Concentration inequalities and large deviations for continuous greedy animals and paths

Julien Verges

Consider the continuous greedy paths model: given a -dimensional Poisson point process with positive marks interpreted as masses, let denote the maximum mass g…

math.PR2024

Large deviation principle at speed for the random metric in first-passage percolation

Julien Verges

Consider standard first-passage percolation on . We study the lower-tail large deviations of the rescaled random metric restricted to a box. If…

cs.CV2024★ 3 cited

Mask of truth: model sensitivity to unexpected regions of medical images

Théo Sourget, Michelle Hestbek-Møller, Amelia Jiménez-Sánchez +2

The development of larger models for medical image analysis has led to increased performance. However, it also affected our ability to explain and validate model decisions. Models…

math.PR2024

Law of large numbers for greedy animals and paths in an ergodic environment

Julien Verges

Consider a family of random masses indexed by vertices of the lattice . In the case where the masses are i.i.d.\ and satisfy a certain moment condition…

math.PR2024★ 1 cited

Large deviation principle at speed for the random metric in first-passage percolation

Julien Verges

We consider the standard first passage percolation model on with bounded weights. We show a large deviation estimate for the probability that the rescaled passage tim…

math.ST2024

Minimax density estimation in the adversarial framework under local differential privacy

Mélisande Albert, Juliette Chevallier, Béatrice Laurent +1

We consider the problem of nonparametric density estimation under privacy constraints in an adversarial framework. To this end, we study minimax rates over Sobolev spaces under loc…