168 citations · 234 across the 10 of their papers we have counts for
10 papers
Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization
Mathieu Even, Laurent Massoulié
Dimension is an inherent bottleneck to some modern learning tasks, where optimization methods suffer from the size of the data. In this paper, we study non-isotropic distributions…
Impossibility of Partial Recovery in the Graph Alignment Problem
Luca Ganassali, Laurent Massoulié, Marc Lelarge
Random graph alignment refers to recovering the underlying vertex correspondence between two random graphs with correlated edges. This can be viewed as an average-case and noisy ve…
Asynchrony and Acceleration in Gossip Algorithms
Mathieu Even, Hadrien Hendrikx, Laurent Massoulié
This paper considers the minimization of a sum of smooth and strongly convex functions dispatched over the nodes of a communication network. Previous works on the subject either fo…
Probabilistic and mean-field model of COVID-19 epidemics with user mobility and contact tracing
M. Akian, L. Ganassali, S. Gaubert +1
We propose a detailed discrete-time model of COVID-19 epidemics coming in two flavours, mean-field and probabilistic. The main contribution lies in several extensions of the basic…
Partial Recovery in the Graph Alignment Problem
Georgina Hall, Laurent Massoulié
In this paper, we consider the graph alignment problem, which is the problem of recovering, given two graphs, a one-to-one mapping between nodes that maximizes edge overlap. This p…
Dual-Free Stochastic Decentralized Optimization with Variance Reduction
Hadrien Hendrikx, Francis Bach, Laurent Massoulié
We consider the problem of training machine learning models on distributed data in a decentralized way. For finite-sum problems, fast single-machine algorithms for large datasets r…
Non-backtracking spectra of weighted inhomogeneous random graphs
Ludovic Stephan, Laurent Massoulié
We study a model of random graphs where each edge is drawn independently (but not necessarily identically distributed) from the others, and then assigned a random weight. When the…
From tree matching to sparse graph alignment
Luca Ganassali, Laurent Massoulié
In this paper we consider alignment of sparse graphs, for which we introduce the Neighborhood Tree Matching Algorithm (NTMA). For correlated Erdős-Rényi random graphs, we prove tha…
Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives
Hadrien Hendrikx, Francis Bach, Laurent Massoulié
In this paper, we study the problem of minimizing a sum of smooth and strongly convex functions split over the nodes of a network in a decentralized fashion. We propose the algorit…
Structural properties of proportional fairness: stability and insensitivity
Laurent Massoulié
In this article we provide a novel characterization of the proportionally fair bandwidth allocation of network capacities, in terms of the Fenchel--Legendre transform of the networ…