activity
20082021
most citedA Semi-Definite Programming approach to low dimensional embedding for unsupervised clustering

6 citations · 14 across the 27 of their papers we have counts for

collaborators

32 papers

math.OC2021

An SDP dual relaxation for the Robust Shortest Path Problem with ellipsoidal uncertainty: Pierra's decomposition method and a new primal Frank-Wolfe-type heuristics for duality gap evaluation

Chifaa Al Dahik, Zeina Al Masry, Stéphane Chrétien +2

This work addresses the Robust counterpart of the Shortest Path Problem (RSPP) with a correlated uncertainty set. Since this problem is hard, a heuristic approach, based on Frank-W…

stat.ML2020★ 2 cited

A finite sample analysis of the benign overfitting phenomenon for ridge function estimation

Emmanuel Caron, Stephane Chretien

Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the samp…

math.OC2019

The dual approach to non-negative super-resolution: impact on primal reconstruction accuracy

Stephane Chretien, Andrew Thompson, Bogdan Toader

We study the problem of super-resolution, where we recover the locations and weights of non-negative point sources from a few samples of their convolution with a Gaussian kernel. I…

cs.LG2019

Revisiting clustering as matrix factorisation on the Stiefel manifold

Stéphane Chrétien, Benjamin Guedj

This paper studies clustering for possibly high dimensional data (e.g. images, time series, gene expression data, and many other settings), and rephrase it as low rank matrix estim…

math.NA2018

A note on computing the Smallest Conic Singular Value

Stephane Chretien

The goal of this note is to study the smallest conic singular value of a matrix from a Lagrangian duality viewpoint and provide an efficient method for its computation.

cs.IT2018

Multi-kernel unmixing and super-resolution using the Modified Matrix Pencil method

Stéphane Chrétien, Hemant Tyagi

Consider groups of point sources or spike trains, with the group represented by . For a function , let $g_l(t) = g(…