
On the Universality of Graph Neural Networks on Large Random Graphs
We study the approximation power of Graph Neural Networks (GNNs) on late...
read it

Fast Graph Kernel with Optical Random Features
The graphlet kernel is a classical method in graph classification. It ho...
read it

Sketching Datasets for LargeScale Learning (long version)
This article considers "sketched learning," or "compressive learning," a...
read it

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs
We study properties of Graph Convolutional Networks (GCNs) by analyzing ...
read it

Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling
We provide statistical learning guarantees for two unsupervised learning...
read it

Sparse and Smooth: improved guarantees for Spectral Clustering in the Dynamic Stochastic Block Model
In this paper, we analyse classical variants of the Spectral Clustering ...
read it

Universal Invariant and Equivariant Graph Neural Networks
Graph Neural Networks (GNN) come in many flavors, but should always be e...
read it

Support Localization and the Fisher Metric for offthegrid Sparse Regularization
Sparse regularization is a central technique for both machine learning (...
read it

NEWMA: a new method for scalable modelfree online changepoint detection
We consider the problem of detecting abrupt changes in the distribution ...
read it

Instance Optimal Decoding and the Restricted Isometry Property
In this paper, we study the preservation of information in illposed non...
read it

A Dual Certificates Analysis of Compressive OfftheGrid Recovery
Many problems in machine learning and imaging can be framed as an infini...
read it

Blind Source Separation Using Mixtures of AlphaStable Distributions
We propose a new blind source separation algorithm based on mixtures of ...
read it

Compressive Statistical Learning with Random Feature Moments
We describe a general framework compressive statistical learning for...
read it

Compressive Kmeans
The LloydMax algorithm is a classical approach to perform Kmeans clust...
read it

Sketching for LargeScale Learning of Mixture Models
Learning parameters from voluminous data can be prohibitive in terms of ...
read it
Nicolas Keriven
verfied profile