Fabian Pedregosa

Fabian Pedregosa

I am a research scientist in the Brain group in Montreal. My main area of expertise is optimization. My previous work includes analysis and development of parallel stochastic methods, the development of more practical methods for optimizing non-smooth functions and new methods for smooth hyperparameter optimization. More broadly, I'm interested in optimization, machine learning and scientific software.

I am also one of the founders of the scikit-learn machine learning library, of which I have been core developer and maintainer from 2010 to 2012, and I have been an active contributor to many open source projects including the computer algebra system sympy and the python profiler memory-profiler.

My current editorial involvement includes being the managing editor of the journal of machine learning research (JMLR) and reviewer for the conferences NIPS and ICML and the journals Mathematical Programming, JMLR.

Finally, I maintain a blog about my research at http://fa.bianp.net.

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Super-Acceleration with Cyclical Step-sizes
Baptiste Goujaud
Damien Scieur
Aymeric Dieuleveut
Adrien B. Taylor
Fabian Pedregosa
Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR (2022)
GradMax: Growing Neural Networks using Gradient Information
Utku Evci
Bart van Merriënboer
Thomas Unterthiner
Max Vladymyrov
Fabian Pedregosa
The International Conference on Learning Representations (2022)
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality
Courtney Paquette
Elliot Paquette
Fabian Pedregosa
Kiwon Lee
Proceedings of Machine Learning Research (2021)
Average-case Acceleration for Bilinear Games and Normal Matrices
Carles Domingo-Enrich
Damien Scieur
Fabian Pedregosa
International Conference on Learning Representations (2021)
Average-case Acceleration Through Spectral Density Estimation
Fabian Pedregosa
Damien Scieur
Proceedings of the 37th International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research (2020)
Universal Average-Case Optimality of Polyak Momentum
Damien Scieur
Fabian Pedregosa
Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research (2020)
Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization
Geoffrey Negiar
Gideon Dresdner
Alicia Tsai
Laurent El Ghaoui
Francesco Locatello
Fabian Pedregosa
Proceedings of the 37th International Conference on Machine Learning (ICML) (2020)
On the interplay between noise and curvature and its effect on optimization and generalization
Valentin Thomas
Fabian Pedregosa
Bart van Merriënboer
Pierre-Antoine Manzagol
Yoshua Bengio
Nicolas Le Roux
Proceedings of the 23rdInternational Conference on Artificial Intelligence and Statistics (AISTATS) (2020)
Linearly Convergent Frank-Wolfe with Backtracking Line-Search
Fabian Pedregosa
Geoffrey Negiar
Armin Askari
Martin Jaggi
Proceedings of the 23rdInternational Conference on Artificial Intelligence and Statistics (AISTATS) (2020)
Search on Google Scholar