National audienceWe explore the use of Optical Processing Units (OPU) to compute random Fourier features for sketching, and adapt the overall compressive clustering pipeline to this setting. We also propose some tools to help tuning a critical hyper-parameter of compressive clustering.Nous proposons une procédure de sketching pour le clustering compressif utilisant des processeurs optiques (OPU) pour calculer les composantes de Fourier alatoires. Cette procédure fait intervenir une stratégie novatrice qui permet de choisir efficacement l'échelle du sketch
This article considers "compressive learning," an approach to large-scale machine learning where dat...
International audienceSpectral clustering has become a popular technique due to its high performance...
The recent framework of compressive statistical learning proposes to design tractable learning algor...
National audienceWe explore the use of Optical Processing Units (OPU) to compute random Fourier feat...
It is an extended version of https://hal.inria.fr/hal-03350599 (official version published with DOI:...
Main novelties between version 1 and version 2: improved concentration bounds, improved sketch sizes...
International audienceIn sketched clustering, a dataset of T samples is first sketched down to a vec...
International audienceThe Lloyd-Max algorithm is a classical approach to perform K-means clustering....
International audienceIn this paper, we address the problem of high-dimensional k-means clustering i...
This preprint results from a split and profound restructuring and improvements of of https://hal.inr...
This article considers "compressive learning," an approach to large-scale machine learning where dat...
International audienceSpectral clustering has become a popular technique due to its high performance...
The recent framework of compressive statistical learning proposes to design tractable learning algor...
National audienceWe explore the use of Optical Processing Units (OPU) to compute random Fourier feat...
It is an extended version of https://hal.inria.fr/hal-03350599 (official version published with DOI:...
Main novelties between version 1 and version 2: improved concentration bounds, improved sketch sizes...
International audienceIn sketched clustering, a dataset of T samples is first sketched down to a vec...
International audienceThe Lloyd-Max algorithm is a classical approach to perform K-means clustering....
International audienceIn this paper, we address the problem of high-dimensional k-means clustering i...
This preprint results from a split and profound restructuring and improvements of of https://hal.inr...
This article considers "compressive learning," an approach to large-scale machine learning where dat...
International audienceSpectral clustering has become a popular technique due to its high performance...
The recent framework of compressive statistical learning proposes to design tractable learning algor...