40 citations · 72 across the 18 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
stat.ML2024
A Margin-based Multiclass Generalization Bound via Geometric Complexity
Michael Munn, Benoit Dherin, Javier Gonzalvo
There has been considerable effort to better understand the generalization capabilities of deep neural networks both as a means to unlock a theoretical understanding of their succe…
cs.LG2024
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
Michael Munn, Benoit Dherin, Javier Gonzalvo
Many of the recent remarkable advances in computer vision and language models can be attributed to the success of transfer learning via the pre-training of large foundation models.…
stat.ML2024
Corridor Geometry in Gradient-Based Optimization
Benoit Dherin, Mihaela Rosca
We characterize regions of a loss surface as corridors when the continuous curves of steepest descent -- the solutions of the gradient flow -- become straight lines. We show that c…