Pierre Wolinski

Since September 2024, I have been an associate professor (maître de conférences) in Computer Science, in the MILES project-team, at the LAMSADE, Paris Dauphine University – PSL, France.

I completed my PhD in Machine Learning in March 2020, supervised by Guillaume Charpiat and Yann Ollivier, at the TAU team, LRI.
Here is my CV: [eng].

Thesis: Structural Learning of Neural Networks [PDF file] [link].
Defense carried out on March 6th, 2020.

Interest

deep learning, neural networks (NNs);
theory: optimization, Bayesian/Variational inference;
hyperparameter search, tuning or removal: neural network pruning, learning rate tuning;
other: neural tangent kernels, random weights, weight initialization...

Adapting Newton's Method to Neural Networks through a Summary of Higher-Order Derivatives (2023), P. Wolinski [link] [code]
Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review (2023), M. T. Lê, P. Wolinski, J. Arbel [link]
Rethinking Gauss-Newton for learning over-parameterized models (NeurIPS 2023, poster), M. Arbel, R. Ménégaux, P. Wolinski [link]
Gaussian Pre-Activations in Neural Networks: Myth or Reality? (2022), P. Wolinski, J. Arbel [link] [code]
An Equivalence between Bayesian Priors and Penalties in Variational Inference (2020), P. Wolinski, G. Charpiat, Y. Ollivier [link]
Learning with Random Learning Rates (ECML 2019), L. Blier, P. Wolinski, Y. Ollivier [link] [code]
Asymmetrical Scaling Layers for Stable Network Pruning, P. Wolinski, G. Charpiat, Y. Ollivier [draft]
Consistance des méthodes RKHS dans le cadre de la minimisation d’un risque convexe (Master thesis, 2015), P. Wolinski, supervised by F. d'Alché-Buc, E. Moulines, F. Roueff [link]

2024 – now: associate professor (maître de conférences) in Computer Science, MILES project-team, LAMSADE, Paris Dauphine University – PSL, France.

2021 – 2023: post-doctoral researcher in the Statify team, LJK, Inria Grenoble-Alpes, France (supervised by Julyan Arbel).

2020 – 2021: post-doctoral researcher at the Department of Statistics, University of Oxford, UK (supervised by Judith Rousseau).

2020: PhD in Computer Science, Paris-Saclay University.

2017: Graduate degree in Mathematics (minor in Physics) at the École Normale Supérieure (Paris).

2016: Master degree in Mathematics (Probability and Statistics), Paris-Sud University.

2016 – 2020: PhD student in Computer Science at the TAO/Tau team, LRI, Paris-Sud University/Inria Saclay, France (supervised by Guillaume Charpiat and Yann Ollivier).

2011 – 2016: Math student at the École Normale Supérieure, Paris, France.

2008 – 2011: Physics/Chemistry student in "classe préparatoire".