Pierre Wolinski

According to our database, Pierre Wolinski authored at least 7 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Adapting Newton's Method to Neural Networks through a Summary of Higher-Order Derivatives.

Pierre Wolinski

CoRR, 2023

Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review.

Minh Tri Le, Pierre Wolinski, Julyan Arbel

CoRR, 2023

Rethinking Gauss-Newton for learning over-parameterized models.

Michael Arbel, Romain Menegaux, Pierre Wolinski

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Imposing Gaussian Pre-Activations in a Neural Network.

Pierre Wolinski, Julyan Arbel

CoRR, 2022

2020

Structural Learning of Neural Networks. (Apprentissage de structure pour les réseaux de neurones).

Pierre Wolinski

PhD thesis, 2020

Interpreting a Penalty as the Influence of a Bayesian Prior.

Pierre Wolinski, Guillaume Charpiat, Yann Ollivier

CoRR, 2020

2019

Learning with Random Learning Rates.

Léonard Blier, Pierre Wolinski, Yann Ollivier

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2019