Search Results for author: Nicolas Verzelen

Found 7 papers, 2 papers with code

Covariance Adaptive Best Arm Identification

no code implementations5 Jun 2023 El Mehdi Saad, Gilles Blanchard, Nicolas Verzelen

This framework allows the learner to estimate the covariance among the arms distributions, enabling a more efficient identification of the best arm.

Active Ranking of Experts Based on their Performances in Many Tasks

no code implementations5 Jun 2023 El Mehdi Saad, Nicolas Verzelen, Alexandra Carpentier

We consider the problem of ranking n experts based on their performances on d tasks.

Localization in 1D non-parametric latent space models from pairwise affinities

no code implementations6 Aug 2021 Christophe Giraud, Yann Issartel, Nicolas Verzelen

We consider the problem of estimating latent positions in a one-dimensional torus from pairwise affinities.

Partial recovery bounds for clustering with the relaxed $K$means

no code implementations19 Jul 2018 Christophe Giraud, Nicolas Verzelen

We investigate the clustering performances of the relaxed $K$means in the setting of sub-Gaussian Mixture Model (sGMM) and Stochastic Block Model (SBM).

Clustering Stochastic Block Model

PECOK: a convex optimization approach to variable clustering

1 code implementation16 Jun 2016 Florentina Bunea, Christophe Giraud, Martin Royer, Nicolas Verzelen

The problem of variable clustering is that of grouping similar components of a $p$-dimensional vector $X=(X_{1},\ldots, X_{p})$, and estimating these groups from $n$ independent copies of $X$.

Statistics Theory Statistics Theory

Model Assisted Variable Clustering: Minimax-optimal Recovery and Algorithms

1 code implementation8 Aug 2015 Florentina Bunea, Christophe Giraud, Xi Luo, Martin Royer, Nicolas Verzelen

We quantify the difficulty of clustering data generated from a G-block covariance model in terms of cluster proximity, measured with respect to two related, but different, cluster separation metrics.

Clustering

Community Detection in Sparse Random Networks

no code implementations13 Aug 2013 Ery Arias-Castro, Nicolas Verzelen

This is formalized as testing for the existence of a dense random subgraph in a random graph.

Community Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.