# Pierre Wolinski

I am currently a post-doctoral researcher at the Department of Statistics of the Unversity of Oxford.

I just finished my PhD in Machine Learning, supervised by Guillaume Charpiat and Yann Ollivier, at the TAU team, LRI.

Here is my CV.

Thesis: *Structural Learning of Neural Networks*
[final version].

Defense carried out on March 6th, 2020.

## Interest

- theory: Bayesian/Variational inference, kernel methods;
- AutoML: neural network pruning, neural architecture search;
- other: neural tangent kernels, random weights (Lottery Ticket Hypothesis, Extreme Learning Machines...).

## Publications

*Interpreting a Penalty as the Influence of a Bayesian Prior* (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]

## Curriculum Vitae

- PhD in Computer Science, University Paris-Saclay (formerly University Paris-Sud).
- Graduate degree in Mathematics (Physics option) at the École Normale Supérieure (Paris).
- Master degree in Mathematics (Probability and Statistics), University Paris-Sud.

### Study

2020 - now: post-doctoral researcher at the Department of Statistics of the University of Oxford.

2016 - 2020: PhD student in Computer Science at the team TAU, LRI, University Paris-Sud/Inria, France.

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

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

2008: Baccalauréat.