no code implementations • 7 Feb 2024 • Marie Chavent, Guy Chavent
Block Principal Component Analysis (Block PCA) of a data matrix A, where loadings Z are determined by maximization of AZ 2 over unit norm orthogonal loadings, is difficult to use for the design of sparse PCA by 1 regularization, due to the difficulty of taking care of both the orthogonality constraint on loadings and the non differentiable 1 penalty.
no code implementations • 12 Jul 2017 • Marie Chavent, Vanessa Kuentz-Simonet, Amaury Labenne, Jérôme Saracco
In this paper, we propose a Ward-like hierarchical clustering algorithm including spatial/geographical constraints.
no code implementations • 1 May 2017 • Marie Chavent, Guy Chavent
We address the problem of defining a group sparse formulation for Principal Components Analysis (PCA) - or its equivalent formulations as Low Rank approximation or Dictionary Learning problems - which achieves a compromise between maximizing the variance explained by the components and promoting sparsity of the loadings.
1 code implementation • 24 Aug 2016 • Marie Chavent, Robin Genuer, Jerome Saracco
Numerical performances of the proposed approach are compared with direct applications of random forests and variable selection using random forests on the original p variables.
Statistics Theory Statistics Theory
1 code implementation • 18 Nov 2014 • Marie Chavent, Vanessa Kuentz-Simonet, Amaury Labenne, Jérôme Saracco
Mixed data arise when observations are described by a mixture of numerical and categorical variables.
Computation
no code implementations • NeurIPS 2013 • Adrien Todeschini, François Caron, Marie Chavent
We propose a novel class of algorithms for low rank matrix completion.