Benoit Dherin

Research Scientist, ML Foundations & Algorithms

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Implicit biases in multitask and continual learning from a backward error analysis perspective
Benoit Dherin
Mathematics of Modern Machine Learning Workshop at NeurIPS 2023 (2023)
On a continuous time model of gradient descent dynamics and instability in deep learning
Mihaela Rosca
Yan Wu
Chongli Qin
Benoit Dherin
Transaction of Machine Learning Research (2023)
Morse Neural Networks for Uncertainty Quantification
Benoit Dherin
Clara Huiyi Hu
Jie Ren
Mike Dusenberry
Balaji Lakshminarayanan
ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling (2023)
Why neural networks find simple solutions: the many regularizers of geometric complexity
Benoit Dherin
Michael Munn
Mihaela Rosca
David Barrett
NeurIPS 2022 (2022)
Discretization Drift in Two-Player Games
Mihaela Rosca
Yan Wu
Benoit Dherin
David Barrett
ICML 2021 (2021)
The Geometric Occam's Razor Implicit in Deep Learning
Benoit Dherin
Michael Munn
David Barrett
NeurIPS 2021 workshop (opt2021) (2021)
On the Origin of Implicit Regularization in Stochastic Gradient Descent
Sam Smith
Benoit Dherin
David Barrett
Soham De
ICLR 2021 (2021)
Implicit Gradient Regularization
David Barrett
Benoit Dherin
ICLR 2021 (2021)
Search on Google Scholar