24 citations · 38 across the 12 of their papers we have counts for
12 papers
Signal processing after quadratic random sketching with optical units
Rémi Delogne, Vincent Schellekens, Laurent Daudet +1
Random data sketching (or projection) is now a classical technique enabling, for instance, approximate numerical linear algebra and machine learning algorithms with reduced computa…
Signal processing with optical quadratic random sketches
Rémi Delogne, Vincent Schellekens, Laurent Daudet +1
Random data sketching (or projection) is now a classical technique enabling, for instance, approximate numerical linear algebra and machine learning algorithms with reduced computa…
MM: A general method to perform various data analysis tasks from a differentially private sketch
Florimond Houssiau, Vincent Schellekens, Antoine Chatalic +2
Differential privacy is the standard privacy definition for performing analyses over sensitive data. Yet, its privacy budget bounds the number of tasks an analyst can perform with…
ROP inception: signal estimation with quadratic random sketching
Rémi Delogne, Vincent Schellekens, Laurent Jacques
Rank-one projections (ROP) of matrices and quadratic random sketching of signals support several data processing and machine learning methods, as well as recent imaging application…
Asymmetric compressive learning guarantees with applications to quantized sketches
Vincent Schellekens, Laurent Jacques
The compressive learning framework reduces the computational cost of training on large-scale datasets. In a sketching phase, the data is first compressed to a lightweight sketch ve…
When compressive learning fails: blame the decoder or the sketch?
Vincent Schellekens, Laurent Jacques
In compressive learning, a mixture model (a set of centroids or a Gaussian mixture) is learned from a sketch vector, that serves as a highly compressed representation of the datase…
Sketching Datasets for Large-Scale Learning (long version)
Rémi Gribonval, Antoine Chatalic, Nicolas Keriven +3
This article considers "compressive learning," an approach to large-scale machine learning where datasets are massively compressed before learning (e.g., clustering, classification…
Breaking the waves: asymmetric random periodic features for low-bitrate kernel machines
Vincent Schellekens, Laurent Jacques
Many signal processing and machine learning applications are built from evaluating a kernel on pairs of signals, e.g. to assess the similarity of an incoming query to a database of…
Compressive Learning of Generative Networks
Vincent Schellekens, Laurent Jacques
Generative networks implicitly approximate complex densities from their sampling with impressive accuracy. However, because of the enormous scale of modern datasets, this training…
Compressive Classification (Machine Learning without learning)
Vincent Schellekens, Laurent Jacques
Compressive learning is a framework where (so far unsupervised) learning tasks use not the entire dataset but a compressed summary (sketch) of it. We propose a compressive learning…
Taking the edge off quantization: projected back projection in dithered compressive sensing
Chunlei Xu, Vincent Schellekens, Laurent Jacques
Quantized compressive sensing (QCS) deals with the problem of representing compressive signal measurements with finite precision representation, i.e., a mandatory process in any pr…
Quantized Compressive K-Means
Vincent Schellekens, Laurent Jacques
The recent framework of compressive statistical learning aims at designing tractable learning algorithms that use only a heavily compressed representation-or sketch-of massive data…