Relative stability toward diffeomorphisms indicates performance in deep
nets

Relative stability toward diffeomorphisms indicates performance in deep nets

6 May 2021

Leonardo Petrini

Alessandro Favero

Papers citing "Relative stability toward diffeomorphisms indicates performance in deep nets"

14 / 14 papers shown

Title
How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model Umberto M. Tomasini M. Wyart BDL 23 7 0 16 Apr 2024
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning Yuxiao Wen Arthur Jacot 47 6 0 12 Feb 2024
How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model Francesco Cagnetta Leonardo Petrini Umberto M. Tomasini Alessandro Favero M. Wyart BDL 27 22 0 05 Jul 2023
How deep convolutional neural networks lose spatial information with training Umberto M. Tomasini Leonardo Petrini Francesco Cagnetta M. Wyart 33 9 0 04 Oct 2022
Automatic Data Augmentation via Invariance-Constrained Learning Ignacio Hounie Luiz F. O. Chamon Alejandro Ribeiro 18 10 0 29 Sep 2022
What Can Be Learnt With Wide Convolutional Neural Networks? Francesco Cagnetta Alessandro Favero M. Wyart MLT 25 11 0 01 Aug 2022
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm Lechao Xiao Jeffrey Pennington 21 10 0 11 Jul 2022
Learning sparse features can lead to overfitting in neural networks Leonardo Petrini Francesco Cagnetta Eric Vanden-Eijnden M. Wyart MLT 25 23 0 24 Jun 2022
Data augmentation with mixtures of max-entropy transformations for filling-level classification Apostolos Modas Andrea Cavallaro P. Frossard 12 0 0 08 Mar 2022
Measuring dissimilarity with diffeomorphism invariance Théophile Cantelobre C. Ciliberto Benjamin Guedj Alessandro Rudi 11 1 0 11 Feb 2022
PRIME: A few primitives can boost robustness to common corruptions Apostolos Modas Rahul Rade Guillermo Ortiz-Jiménez Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 16 41 0 27 Dec 2021
On the Sample Complexity of Learning under Invariance and Geometric Stability A. Bietti Luca Venturi Joan Bruna 19 5 0 14 Jun 2021
Geometric compression of invariant manifolds in neural nets J. Paccolat Leonardo Petrini Mario Geiger Kevin Tyloo M. Wyart MLT 47 34 0 22 Jul 2020
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location O. Kayhan J. C. V. Gemert 209 232 0 16 Mar 2020