See also my Google Scholar page.
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
Michael Munn, Benoit Dherin, and Javier Gonzalvo
accepted at NeurIPS 2024
[arXiv]
Leveraging Free Energy in Pretraining Model Selection for Improved Fine-tuning
Michael Munn, Susan Wei, 2024
[arXiv]
A Margin-based Multiclass Generalization Bound via Geometric Complexity
Michael Munn, Benoit Dherin, and Javier Gonzalvo
ICML, TAG-ML 2023
[arXiv] [OpenReview] [Proceedings]
Unified Functional Hashing in Automatic Machine Learning
Ryan Gillard, Stephen Jonany, Yingjie Miao, Michael Munn, Connal de Souza, Jonathan Dungay, Chen Liang, David R. So, Quoc V. Le, and Esteban Real, 2023
[arXiv]
Why neural networks find simple solutions: the many regularizers of geometric complexity
Benoit Dherin, Michael Munn, Mihaela Rosca, and David G. T. Barrett
NeurIPS 2022
[arXiv] [OpenReview] [Proceedings] [Slides]
The Geometric Occam’s Razor Implicit in Deep Learning
Benoit Dherin, Michael Munn, and David G.T. Barrett
NeurIPS, OPT-Optimization in Machine Learning 2021
[arXiv] [Proceedings]
COT-GAN: Generating Sequential Data via Causal Optimal Transport
Tianlin Xu, Li K. Wenliang, Michael Munn, Beatrice Acciaio
NeurIPS 2020
[arXiv] [OpenReview] [Proceedings]
Prior to Google
On Weak Super Ricci Flow through Neckpinch
Sajjad Lakzian, and Michael Munn (alphabetical)
Analysis and Geometry in Metric Spaces 2020
[arXiv] [Journal]
Three-Dimensional Alexandrov spaces with positive or nonnegative Ricci curvature
Qintao Deng, Fernando Galaz-Garcia, Luis Guijarro, Michael Munn (alphabetical)
Potential Analysis 2016
[arXiv] [Journal]
Geometric singularities and a flow tangent to the Ricci flow
Lashi Bandara, Sajjad Lakzian, and Michael Munn (alphabetical).
Annali Scuola Normale Superiore-Classe di Scienze 2015
[arXiv] [Journal]
Intrinsic flat convergence with bounded Ricci curvature
Michael Munn, 2014
[arXiv]
Alexandrov spaces with large volume growth
Michael Munn
Journal of Mathematical Analysis and Applications 2014
[arXiv] [Journal]
On the Size of a Ricci Flow Neckpinch via Optimal Transport
Sajjad Lakzian, and Michael Munn (alphabetical), 2014
[arXiv]
Super Ricci flow for disjoint unions
Sajjad Lakzian, and Michael Munn (alphabetical), 2012
[arXiv]
Volume growth and the topology of Gromov-Hausdorff limits
Michael Munn
Differential Geometry and its Applications 2010
[arXiv] [Journal]
Volume growth and the topology of manifolds with nonnegative Ricci curvature
Michael Munn.
Journal of Geometric Analysis 2009
[arXiv] [Journal]
On the appearance of Eisenstein series through degeneration
Dan Garbin, Jay Jorgenson, and Michael Munn (alphabetical).
Commentarii Mathematici Helvetici 2008
[arXiv] [Journal]