Matthieu Wyart

CoRR, 2024

A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data.

[BibT_eX]

[DOI]

CoRR, 2024

How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model.

[BibT_eX]

[DOI]

Umberto M. Tomasini

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

How deep convolutional neural networks lose spatial information with training.

[BibT_eX]

[DOI]

Mach. Learn. Sci. Technol., December, 2023

On the different regimes of Stochastic Gradient Descent.

[BibT_eX]

[DOI]

CoRR, 2023

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model.

[BibT_eX]

[DOI]

CoRR, 2023

Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

What Can Be Learnt With Wide Convolutional Neural Networks?

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

2022

How Wide Convolutional Neural Networks Learn Hierarchical Tasks.

[BibT_eX]

[DOI]

CoRR, 2022

Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data.

[BibT_eX]

[DOI]

Umberto M. Tomasini

CoRR, 2022

Learning sparse features can lead to overfitting in neural networks.

[BibT_eX]

[DOI]

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

Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data.

[BibT_eX]

[DOI]

Umberto M. Tomasini

Proceedings of the International Conference on Machine Learning, 2022

2021

How isotropic kernels perform on simple invariants.

[BibT_eX]

[DOI]

Jonas Paccolat

Stefano Spigler

Mach. Learn. Sci. Technol., 2021

How memory architecture affects performance and learning in simple POMDPs.

[BibT_eX]

[DOI]

Christophe Eloy

CoRR, 2021

Relative stability toward diffeomorphisms in deep nets indicates performance.

[BibT_eX]

[DOI]

CoRR, 2021

Relative stability toward diffeomorphisms indicates performance in deep nets.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Direct coupling analysis of epistasis in allosteric materials.

[BibT_eX]

[DOI]

PLoS Comput. Biol., 2020

Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training.

[BibT_eX]

[DOI]

Leonardo Petrini

CoRR, 2020

Compressing invariant manifolds in neural nets.

[BibT_eX]

[DOI]

CoRR, 2020

How isotropic kernels learn simple invariants.

[BibT_eX]

[DOI]

Jonas Paccolat

Stefano Spigler

CoRR, 2020

2019

Disentangling feature and lazy learning in deep neural networks: an empirical study.

[BibT_eX]

[DOI]

CoRR, 2019

Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm.

[BibT_eX]

[DOI]

Stefano Spigler

CoRR, 2019

Scaling description of generalization with number of parameters in deep learning.

[BibT_eX]

[DOI]

CoRR, 2019

2018

A jamming transition from under- to over-parametrization affects loss landscape and generalization.

[BibT_eX]

[DOI]

CoRR, 2018

The jamming transition as a paradigm to understand the loss landscape of deep neural networks.

[BibT_eX]

[DOI]

CoRR, 2018

Comparing Dynamics: Deep Neural Networks versus Glassy Systems.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

2013

Simulations of driven overdamped frictionless hard spheres.

[BibT_eX]

[DOI]

Edan Lerner

Gustavo Düring

Comput. Phys. Commun., 2013

2010

Evaluating Gene Expression Dynamics Using Pairwise RNA FISH Data.

[BibT_eX]

[DOI]