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

25 September 2018

Papers citing "The jamming transition as a paradigm to understand the loss landscape of deep neural networks"

22 / 22 papers shown

Title
Investigating the Impact of Model Complexity in Large Language Models Jing Luo Huiyuan Wang Weiran Huang 34 0 0 01 Oct 2024
How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning Arthur Jacot Seok Hoan Choi Yuxiao Wen AI4CE 91 2 0 08 Jul 2024
Gibbs-Based Information Criteria and the Over-Parameterized Regime Haobo Chen Yuheng Bu Greg Wornell 27 1 0 08 Jun 2023
Can we avoid Double Descent in Deep Neural Networks? Victor Quétu Enzo Tartaglione AI4CE 20 3 0 26 Feb 2023
On the Lipschitz Constant of Deep Networks and Double Descent Matteo Gamba Hossein Azizpour Marten Bjorkman 25 7 0 28 Jan 2023
REPAIR: REnormalizing Permuted Activations for Interpolation Repair Keller Jordan Hanie Sedghi O. Saukh R. Entezari Behnam Neyshabur MoMe 46 94 0 15 Nov 2022
A Solvable Model of Neural Scaling Laws A. Maloney Daniel A. Roberts J. Sully 31 51 0 30 Oct 2022
Deep Double Descent via Smooth Interpolation Matteo Gamba Erik Englesson Marten Bjorkman Hossein Azizpour 59 10 0 21 Sep 2022
Information FOMO: The unhealthy fear of missing out on information. A method for removing misleading data for healthier models Ethan Pickering T. Sapsis 18 6 0 27 Aug 2022
A generalization gap estimation for overparameterized models via the Langevin functional variance Akifumi Okuno Keisuke Yano 30 1 0 07 Dec 2021
Multi-scale Feature Learning Dynamics: Insights for Double Descent Mohammad Pezeshki Amartya Mitra Yoshua Bengio Guillaume Lajoie 61 25 0 06 Dec 2021
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks R. Entezari Hanie Sedghi O. Saukh Behnam Neyshabur MoMe 37 215 0 12 Oct 2021
Classification and Adversarial examples in an Overparameterized Linear Model: A Signal Processing Perspective Adhyyan Narang Vidya Muthukumar A. Sahai SILM AAML 33 1 0 27 Sep 2021
Multiple Descent: Design Your Own Generalization Curve Lin Chen Yifei Min M. Belkin Amin Karbasi DRL 18 61 0 03 Aug 2020
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them Chen Liu Mathieu Salzmann Tao R. Lin Ryota Tomioka Sabine Süsstrunk AAML 19 81 0 15 Jun 2020
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks Z. Fan Zhichao Wang 34 71 0 25 May 2020
Classification vs regression in overparameterized regimes: Does the loss function matter? Vidya Muthukumar Adhyyan Narang Vignesh Subramanian M. Belkin Daniel J. Hsu A. Sahai 36 148 0 16 May 2020
In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors Jeffrey Negrea Gintare Karolina Dziugaite Daniel M. Roy AI4CE 24 64 0 09 Dec 2019
From complex to simple : hierarchical free-energy landscape renormalized in deep neural networks H. Yoshino 14 6 0 22 Oct 2019
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks Umut Simsekli Levent Sagun Mert Gurbuzbalaban 17 237 0 18 Jan 2019
Scaling description of generalization with number of parameters in deep learning Mario Geiger Arthur Jacot S. Spigler Franck Gabriel Levent Sagun Stéphane dÁscoli Giulio Biroli Clément Hongler M. Wyart 39 194 0 06 Jan 2019
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 179 1,185 0 30 Nov 2014