Random Matrix Theory Proves that Deep Learning Representations of
GAN-data Behave as Gaussian Mixtures

Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures

21 January 2020

Romain Couillet

Papers citing "Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures"

17 / 17 papers shown

Title
Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure Samet Demir Zafer Dogan MLT 34 0 0 02 Mar 2025
Gramian Multimodal Representation Learning and Alignment Giordano Cicchetti Eleonora Grassucci Luigi Sigillo Danilo Comminiello 99 1 0 16 Dec 2024
Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets Khen Cohen Noam Levi Yaron Oz BDL 31 1 0 28 May 2024
Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption Vasilii Feofanov Malik Tiomoko Aladin Virmaux 33 5 0 20 Oct 2023
How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features Simone Bombari Marco Mondelli AAML 42 5 0 20 May 2023
Precise Asymptotic Analysis of Deep Random Feature Models David Bosch Ashkan Panahi B. Hassibi 35 19 0 13 Feb 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels Simone Bombari Shayan Kiyani Marco Mondelli AAML 46 10 0 03 Feb 2023
On some theoretical limitations of Generative Adversarial Networks Benoit Oriol Alexandre Miot GAN 11 4 0 21 Oct 2021
Spectral properties of sample covariance matrices arising from random matrices with independent non identically distributed columns Cosme Louart Romain Couillet 14 7 0 06 Sep 2021
Node Feature Kernels Increase Graph Convolutional Network Robustness M. Seddik Changmin Wu J. Lutzeyer Michalis Vazirgiannis AAML 32 8 0 04 Sep 2021
Learning curves of generic features maps for realistic datasets with a teacher-student model Bruno Loureiro Cédric Gerbelot Hugo Cui Sebastian Goldt Florent Krzakala M. Mézard Lenka Zdeborová 35 136 0 16 Feb 2021
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks Quynh N. Nguyen Marco Mondelli Guido Montúfar 25 81 0 21 Dec 2020
The Gaussian equivalence of generative models for learning with shallow neural networks Sebastian Goldt Bruno Loureiro Galen Reeves Florent Krzakala M. Mézard Lenka Zdeborová BDL 41 100 0 25 Jun 2020
Provable tradeoffs in adversarially robust classification Yan Sun Hamed Hassani David Hong Alexander Robey 23 53 0 09 Jun 2020
Generalisation error in learning with random features and the hidden manifold model Federica Gerace Bruno Loureiro Florent Krzakala M. Mézard Lenka Zdeborová 25 166 0 21 Feb 2020
Geometric Dataset Distances via Optimal Transport David Alvarez-Melis Nicolò Fusi OT 85 194 0 07 Feb 2020
Minimax testing of a composite null hypothesis defined via a quadratic functional in the model of regression L. Comminges A. Dalalyan 71 58 0 09 Aug 2012