Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra

27 August 2020

Papers citing "Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra"

23 / 23 papers shown

Title
Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse Kun He Zijian Song Shuoxi Zhang J. Hopcroft CLL 56 0 0 25 Apr 2025
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis Weronika Ormaniec Felix Dangel Sidak Pal Singh 33 6 0 14 Oct 2024
Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes Nikita Kiselev Andrey Grabovoy 41 1 0 18 Sep 2024
Linguistic Collapse: Neural Collapse in (Large) Language Models Robert Wu V. Papyan 48 12 0 28 May 2024
Gradients of Functions of Large Matrices Nicholas Krämer Pablo Moreno-Muñoz Hrittik Roy Søren Hauberg 34 0 0 27 May 2024
Does SGD really happen in tiny subspaces? Minhak Song Kwangjun Ahn Chulhee Yun 66 4 1 25 May 2024
Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization Zhe Li Bicheng Ying Zidong Liu Haibo Yang Haibo Yang FedML 59 3 0 24 May 2024
The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank Amitay Bar Rotem Mulayoff T. Michaeli Ronen Talmon 61 0 0 21 Feb 2024
Neural Collapse in Multi-label Learning with Pick-all-label Loss Pengyu Li Xiao Li Yutong Wang Qing Qu 22 8 0 24 Oct 2023
Generalized Neural Collapse for a Large Number of Classes Jiachen Jiang Jinxin Zhou Peng Wang Qing Qu Dustin Mixon Chong You Zhihui Zhu AI4CE 32 23 0 09 Oct 2023
Spectral alignment of stochastic gradient descent for high-dimensional classification tasks Gerard Ben Arous Reza Gheissari Jiaoyang Huang Aukosh Jagannath 27 14 0 04 Oct 2023
Principled and Efficient Transfer Learning of Deep Models via Neural Collapse Xiao Li Sheng Liu Jin-li Zhou Xin Lu C. Fernandez‐Granda Zhihui Zhu Q. Qu AAML 23 18 0 23 Dec 2022
A Law of Data Separation in Deep Learning Hangfeng He Weijie J. Su OOD 24 36 0 31 Oct 2022
Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning Shuo Xie Jiahao Qiu Ankita Pasad Li Du Qing Qu Hongyuan Mei 32 16 0 18 Oct 2022
Are All Losses Created Equal: A Neural Collapse Perspective Jinxin Zhou Chong You Xiao Li Kangning Liu Sheng Liu Qing Qu Zhihui Zhu 30 58 0 04 Oct 2022
Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold Can Yaras Peng Wang Zhihui Zhu Laura Balzano Qing Qu 15 41 0 19 Sep 2022
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness J. Liu Shreyas Padhy Jie Jessie Ren Zi Lin Yeming Wen Ghassen Jerfel Zachary Nado Jasper Snoek Dustin Tran Balaji Lakshminarayanan UQCV BDL 16 48 0 01 May 2022
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features Jinxin Zhou Xiao Li Tian Ding Chong You Qing Qu Zhihui Zhu 22 97 0 02 Mar 2022
Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping Xuran Meng Jianfeng Yao 17 7 0 26 Nov 2021
MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning Siladittya Manna Umapada Pal Saumik Bhattacharya SSL 35 1 0 24 Nov 2021
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training Diego Granziol S. Zohren Stephen J. Roberts ODL 29 48 0 16 Jun 2020
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 159 234 0 04 Mar 2020
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 281 2,888 0 15 Sep 2016