Benoit Dherin

According to our database, Benoit Dherin authored at least 10 papers between 2021 and 2024.

Collaborative distances:

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

2024

Corridor Geometry in Gradient-Based Optimization.

Benoit Dherin, Mihaela Rosca

CoRR, 2024

2023

On a continuous time model of gradient descent dynamics and instability in deep learning.

Mihaela Rosca, Yan Wu, Chongli Qin, Benoit Dherin

Trans. Mach. Learn. Res., 2023

Implicit biases in multitask and continual learning from a backward error analysis perspective.

Benoit Dherin

CoRR, 2023

Morse Neural Networks for Uncertainty Quantification.

Benoit Dherin, Huiyi Hu, Jie Ren, Michael W. Dusenberry, Balaji Lakshminarayanan

CoRR, 2023

A margin-based multiclass generalization bound via geometric complexity.

Michael Munn, Benoit Dherin, Javier Gonzalvo

Proceedings of the Topological, 2023

2022

Why neural networks find simple solutions: The many regularizers of geometric complexity.

Benoit Dherin, Michael Munn, Mihaela Rosca, David Barrett

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

The Geometric Occam's Razor Implicit in Deep Learning.

Benoit Dherin, Michael Munn, David G. T. Barrett

CoRR, 2021

Discretization Drift in Two-Player Games.

Mihaela Rosca, Yan Wu, Benoit Dherin, David Barrett

Proceedings of the 38th International Conference on Machine Learning, 2021

On the Origin of Implicit Regularization in Stochastic Gradient Descent.

Samuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De

Proceedings of the 9th International Conference on Learning Representations, 2021

Implicit Gradient Regularization.

David G. T. Barrett, Benoit Dherin

Proceedings of the 9th International Conference on Learning Representations, 2021