67 citations
- Computer Algorithms for MedicineAT9 papers
- Institut national de recherche en sciences et technologies du numériqueFR7 papers
- Institut de Mathématiques de Jussieu-Paris Rive GaucheFR4 papers
- Centre Inria de l'Université de LorraineFR3 papers
- Département d'InformatiqueFR3 papers
- École Normale Supérieure - PSLFR3 papers
- École PolytechniqueFR3 papers
- Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsFR3 papers
- Microsoft Research (India)IN3 papers
- OURAGAN: Outils de Résolution Algébriques pour la Géométrie et ses ApplicationsFR3 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
6 papers · 1 filter
Online greedy identification of linear dynamical systems
Matthieu Blanke, Marc Lelarge
This work addresses the problem of exploration in an unknown environment. For linear dynamical systems, we use an experimental design framework and introduce an online greedy polic…
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…
Sharp threshold for alignment of graph databases with Gaussian weights
Luca Ganassali
We study the fundamental limits for reconstruction in weighted graph (or matrix) database alignment. We consider a model of two graphs where is a planted uniform permutation…
Graph Spectral Embedding for Parsimonious Transmission of Multivariate Time Series
Lihan Yao, Paul Bendich
We propose a graph spectral representation of time series data that 1) is parsimoniously encoded to user-demanded resolution; 2) is unsupervised and performant in data-constrained…
Reconstruction in the Labeled Stochastic Block Model
Marc Lelarge, Laurent Massoulié, Jiaming Xu
The labeled stochastic block model is a random graph model representing networks with community structure and interactions of multiple types. In its simplest form, it consists of t…