Vincent Schellekens
researcher in sustainable AI

Pending publications

1. Asymmetric compressive learning guarantees with applications to quantized sketches
   Vincent Schellekens, Laurent Jacques
   Submitted.

   arXiv

   (More)

Thesis

1. Extending the Compressive Statistical Learning Framework: Quantization, Privacy, and Beyond

   

   
   Vincent Schellekens

   (More)

Journal papers

1. Sketching Datasets for Large-Scale Learning
   Rémi Gribonval, Antoine Chatalic, Nicolas Keriven, Vincent Schellekens, Laurent Jacques, Philip Schniter
   Accepted in: IEEE Signal Processing Magasine, September 2021.

   arXiv

   (More)
2. Breaking the waves: asymmetric random periodic features for low-bitrate kernel machines

   

   
   Vincent Schellekens, Laurent Jacques
   Accepted in: Information and Inference: A Journal of the IMA.

   arXiv

   (More)
3. Compressive Learning with Privacy Guarantees
   Antoine Chatalic, Vincent Schellekens, Florimond Houssiau, Yves-Alexandre de Montjoye, Laurent Jacques, Rémi Gribonval
   Accepted in: Information and Inference: A Journal of the IMA.

   HAL

   (More)
4. Quantized Compressive K-Means

   

   
   Vincent Schellekens, Laurent Jacques
   In: IEEE Signal Processing Letters, Vol. 25, no. 8, p. 1211-1215, 2018.

   DOI; arXiv; dial

   (More)

Conference/workshop papers

1. When compressive learning fails: blame the decoder or the sketch?

   

   
   Vincent Schellekens, Laurent Jacques
   Accepted at the iTWIST'20 workshop.
2. Compressive Learning of Generative Networks

   

   
   Vincent Schellekens, Laurent Jacques
   Accepted at: ESANN'20, Bruges, Belgium.

   arXiv;

   (More)
3. Compressive k-Means with Differential Privacy

   

   
   Vincent Schellekens, Antoine Chatalic, Florimond Houssiau, Yves-Alexandre de Montjoye, Laurent Jacques, Rémi Gribonval
   Accepted at SPARS'19, Toulouse, France.

   (More)
4. Differentially Private Compressive K-Means

   

   
   Vincent Schellekens, Antoine Chatalic, Florimond Houssiau, Yves-Alexandre de Montjoye, Laurent Jacques, Rémi Gribonval
   Accepted at ICASSP'19, Brighton, UK.

   dial; HAL

   (More)
5. Compressive Classification (Machine Learning without learning)

   

   
   Vincent Schellekens, Laurent Jacques
   In: proceedings of the iTWIST'18 workshop, Marseille (France), 2018.

   arXiv; dial

   (More)
6. Taking the edge off quantization: projected back projection in dithered compressive sensing
   Chunlei Xu, Vincent Schellekens, Laurent Jacques
   In: 2018 IEEE Statistical Signal Processing Workshop (SSP), 2018.

   arXiv; dial

   (More)

Other oral presentations

1. Generative models as data-driven priors: how to learn them efficiently?

   

   
   Presented at FNRS Contact Group "Wavelets and applications" 2019 meeting (22/11/2019).

   (More)