MVA

The MVA (Mathematics, Vision, Learning) is a master of research at École Normale Supérieure Paris-Saclay. I followed it as part of a dual degree with Mines Paris during the year 2021-2022. As many people asked me about my experience during this year, I decided to make it available to everybody! (writing in progress...)

Sub-pixel image processing (Lionel MOISAN)

Project: Elliptical phantoms for tomographic reconstruction 📉 Report / Slides / Code.

Homeworks: 11 practical homeworks written in LaTeX.

Grade: 18/20.

Computational optimal transport (Gabriel PEYRE)

Project: Paper review + implementation: Solomon, J. et al. (2014) ‘Earth mover’s distances on discrete surfaces’, ACM Transactions on Graphics 📉 Report / Slides / GIF.

Homeworks: 4 `Numerical Tours' on Jupyter Notebooks.

Grade: 17/20.

Kernel methods for machine learning (Julien MAIRAL, Michael ARBEL)

Project: Written exam + Kaggle data challenge 📉 Report.

Homeworks: 4 written sets of exercises.

Grade: 18.2/20.

Computational statistics (Stéphanie ALLASSONIERE)

Project (w/ Théo Dumont): Paper review: Arvanitidis, G., Hansen, L.K. and Hauberg, S. (2018) ‘Latent Space Oddity: on the Curvature of Deep Generative Models’, ICLR 📉 Slides.

Homeworks: 4 Jupyter Notebooks: Markov Chains -- Stochastic Gradient Descent, Expectation-Maximization -- Importance sampling, Hasting-Metropolis and Gibbs samplers, Adaptive Metropolis-Hastings and parallel tempering.

Grade: 18.2/20.

Geometry of shape spaces (Alain TROUVE, Joan Alexis GLAUNES)

Project: Paper review (on the blackboard): Younes, L. (2020) ‘Diffeomorphic Learning’, JMLR.

Homeworks: 2 Jupyter Notebooks (kernel regression + shape registration with LDDMM) + math exercises.

Grade: 17.5/20.

Medical Image Analysis based on generative, geometric and biophysical models (Xavier PENNEC, Hervé DELINGETTE)

Project (w/ Arthur Pignet): Paper review + implementation: Mallasto, A. and Feragen, A. (2018) ‘Wrapped Gaussian Process Regression on Riemannian Manifolds’, CVPR 📉 Report / Slides.
Submitted and awarded 2nd prize at the ICLR 2022 Challenge for Computational Geometry and Topology. Submissions / Post.

Grade: 17/20.

Functional brain imaging (Bertrand THIRION, Théodore PAPADOPOULO)

Project: Voxel-based Morphometry on Oasis dataset with Space-Net prior.

Grade: 17/20.

Convex optimization and applications in machine learning (Alexandre D’ASPREMONT)

Project: Written exam.

Homeworks: Handwritten exercises + implementation of the LASSO with a barrier method.

Grade: 15/20.

Geometry and statistical learning (Stanley DURRLEMAN)

Project: Paper review and implementation: Lorenzi, M. and Pennec, X. (2014) ‘Efficient Parallel Transport of Deformations in Time Series of Images: From Schild’s to Pole Ladder’, JMIV. 📉 Slides.

Grade: 13/20.

Page updated

Google Sites

Report abuse