Alert button
Picture for Benoit Dherin

Benoit Dherin

Alert button

Corridor Geometry in Gradient-Based Optimization

Feb 13, 2024
Benoit Dherin, Mihaela Rosca

Viaarxiv icon

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

Nov 01, 2023
Benoit Dherin

Viaarxiv icon

Morse Neural Networks for Uncertainty Quantification

Jul 02, 2023
Benoit Dherin, Huiyi Hu, Jie Ren, Michael W. Dusenberry, Balaji Lakshminarayanan

Figure 1 for Morse Neural Networks for Uncertainty Quantification
Figure 2 for Morse Neural Networks for Uncertainty Quantification
Figure 3 for Morse Neural Networks for Uncertainty Quantification
Viaarxiv icon

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

Feb 03, 2023
Mihaela Rosca, Yan Wu, Chongli Qin, Benoit Dherin

Figure 1 for On a continuous time model of gradient descent dynamics and instability in deep learning
Figure 2 for On a continuous time model of gradient descent dynamics and instability in deep learning
Figure 3 for On a continuous time model of gradient descent dynamics and instability in deep learning
Figure 4 for On a continuous time model of gradient descent dynamics and instability in deep learning
Viaarxiv icon

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

Sep 27, 2022
Benoit Dherin, Michael Munn, Mihaela Rosca, David G. T. Barrett

Figure 1 for Why neural networks find simple solutions: the many regularizers of geometric complexity
Figure 2 for Why neural networks find simple solutions: the many regularizers of geometric complexity
Figure 3 for Why neural networks find simple solutions: the many regularizers of geometric complexity
Figure 4 for Why neural networks find simple solutions: the many regularizers of geometric complexity
Viaarxiv icon

The Geometric Occam's Razor Implicit in Deep Learning

Dec 01, 2021
Benoit Dherin, Michael Munn, David G. T. Barrett

Figure 1 for The Geometric Occam's Razor Implicit in Deep Learning
Figure 2 for The Geometric Occam's Razor Implicit in Deep Learning
Viaarxiv icon

Discretization Drift in Two-Player Games

May 28, 2021
Mihaela Rosca, Yan Wu, Benoit Dherin, David G. T. Barrett

Figure 1 for Discretization Drift in Two-Player Games
Figure 2 for Discretization Drift in Two-Player Games
Figure 3 for Discretization Drift in Two-Player Games
Figure 4 for Discretization Drift in Two-Player Games
Viaarxiv icon

On the Origin of Implicit Regularization in Stochastic Gradient Descent

Jan 28, 2021
Samuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De

Figure 1 for On the Origin of Implicit Regularization in Stochastic Gradient Descent
Figure 2 for On the Origin of Implicit Regularization in Stochastic Gradient Descent
Figure 3 for On the Origin of Implicit Regularization in Stochastic Gradient Descent
Figure 4 for On the Origin of Implicit Regularization in Stochastic Gradient Descent
Viaarxiv icon

Implicit Gradient Regularization

Sep 23, 2020
David G. T. Barrett, Benoit Dherin

Figure 1 for Implicit Gradient Regularization
Figure 2 for Implicit Gradient Regularization
Figure 3 for Implicit Gradient Regularization
Figure 4 for Implicit Gradient Regularization
Viaarxiv icon