Asymptotics of feature learning in two-layer networks after one
gradient-step

Asymptotics of feature learning in two-layer networks after one gradient-step

7 February 2024

Florent Krzakala

Lenka Zdeborová

Papers citing "Asymptotics of feature learning in two-layer networks after one gradient-step"

15 / 15 papers shown

Title
Survey on Algorithms for multi-index models Joan Bruna Daniel Hsu 18 0 0 07 Apr 2025
Deep Neural Nets as Hamiltonians Mike Winer Boris Hanin 49 0 0 31 Mar 2025
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
A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities Yatin Dandi Luca Pesce Hugo Cui Florent Krzakala Yue M. Lu Bruno Loureiro MLT 35 1 0 24 Oct 2024
Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods Hossein Taheri Christos Thrampoulidis Arya Mazumdar MLT 26 0 0 13 Oct 2024
Random Features Outperform Linear Models: Effect of Strong Input-Label Correlation in Spiked Covariance Data Samet Demir Zafer Dogan 28 1 0 30 Sep 2024
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks Clémentine Dominé Nicolas Anguita A. Proca Lukas Braun D. Kunin P. Mediano Andrew M. Saxe 30 3 0 22 Sep 2024
A spring-block theory of feature learning in deep neural networks Chengzhi Shi Liming Pan Ivan Dokmanić AI4CE 28 1 0 28 Jul 2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning D. Kunin Allan Raventós Clémentine Dominé Feng Chen David Klindt Andrew M. Saxe Surya Ganguli MLT 24 15 0 10 Jun 2024
Crafting Heavy-Tails in Weight Matrix Spectrum without Gradient Noise Vignesh Kothapalli Tianyu Pang Shenyang Deng Zongmin Liu Yaoqing Yang 26 3 0 07 Jun 2024
Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models Behrad Moniri Hamed Hassani 19 0 0 28 May 2024
Restoring balance: principled under/oversampling of data for optimal classification Emanuele Loffredo Mauro Pastore Simona Cocco R. Monasson 27 9 0 15 May 2024
Asymptotics of Learning with Deep Structured (Random) Features Dominik Schröder Daniil Dmitriev Hugo Cui Bruno Loureiro 32 6 0 21 Feb 2024
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics Emmanuel Abbe Enric Boix-Adserà Theodor Misiakiewicz FedML MLT 76 72 0 21 Feb 2023
Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach Grant M. Rotskoff Eric Vanden-Eijnden 56 114 0 02 May 2018