15 citations · 38 across the 9 of their papers we have counts for
14 papers
The spectral edge of sparse directed Erdös-Rényi graphs
Simon Coste, Yizhe Zhu
Let be fixed and let be an matrix with independent $\Ber(d/n)$ entries. For every , we prove that, with high probability, a positive proportion…
The Wasserstein cost of Importance Sampling
Simon Coste, Michael Goldman
Importance sampling (IS) consists in biasing samples from a distribution towards another distribution . Concretely, given samples from , the IS measure is $$\hat{g}…
The delocalization of eigenvectors of real elliptic matrices
Lucas Benigni, Simon Coste, Guillaume Dubach
We investigate delocalization phenomena for eigenvectors of real random matrices that are invariant by orthogonal transformations. A specific phenomenon with these ensembles is tha…
Random eigenvalues of graphenes and the triangulation of plane
Artur Bille, Victor Buchstaber, Simon Coste +2
We analyse the numbers of closed paths of length on two important regular lattices: the hexagonal lattice (also called in chemistry) and its du…
Efficient Training of Energy-Based Models Using Jarzynski Equality
Davide Carbone, Mengjian Hua, Simon Coste +1
Energy-based models (EBMs) are generative models inspired by statistical physics with a wide range of applications in unsupervised learning. Their performance is best measured by t…
Wavelet Score-Based Generative Modeling
Florentin Guth, Simon Coste, Valentin De Bortoli +1
Score-based generative models (SGMs) synthesize new data samples from Gaussian white noise by running a time-reversed Stochastic Differential Equation (SDE) whose drift coefficient…
The characteristic polynomial of sums of random permutations and regular digraphs
Simon Coste, Gaultier Lambert, Yizhe Zhu
Let be the sum of permutation matrices of size , each drawn uniformly at random and independently. We prove that the normalized characteristic polynomial $\fra…
Sparse matrices: convergence of the characteristic polynomial seen from infinity
Simon Coste
We prove that the reverse characteristic polynomial of a random matrix with iid entries converges in distribution to…
A simpler spectral approach for clustering in directed networks
Simon Coste, Ludovic Stephan
We study the task of clustering in directed networks. We show that using the eigenvalue/eigenvector decomposition of the adjacency matrix is simpler than all common methods which a…
Detection thresholds in very sparse matrix completion
Charles Bordenave, Simon Coste, Raj Rao Nadakuditi
Let be a rectangular matrix of size and be the random matrix where each entry of is multiplied by an independent -Bernoulli random variable with…
Eigenvalues of the non-backtracking operator detached from the bulk
Simon Coste, Yizhe Zhu
We describe the non-backtracking spectrum of a stochastic block model with connection probabilities . In this regime we answer a qu…
Emergence of extended states at zero in the spectrum of sparse random graphs
Simon Coste, Justin Salez
We confirm the long-standing prediction that is the threshold for the emergence of a non-vanishing absolutely continuous part (extended states) at zero in the li…
Graphs with prescribed local neighborhoods of their universal coverings
Charles Bordenave, Simon Coste
Given a collection of n rooted trees with depth h, we give a necessary and sufficient condition for this collection to be the collection of h-depth universal covering neighborhoods…
The Spectral Gap of Sparse Random Digraphs
Simon Coste
The second largest eigenvalue of a transition matrix has connections with many properties of the underlying Markov chain, and especially its convergence rate towards the statio…