Extended Unconstrained Features Model for Exploring Deep Neural Collapse
暂无分享,去创建一个
[1] Zhihui Zhu,et al. On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features , 2022, ICML.
[2] Jianfeng Lu,et al. Neural collapse under cross-entropy loss , 2022, Applied and Computational Harmonic Analysis.
[3] Yiping Lu,et al. An Unconstrained Layer-Peeled Perspective on Neural Collapse , 2021, ICLR.
[4] X. Y. Han,et al. Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path , 2021, ICLR.
[5] Dustin G. Mixon,et al. Neural collapse with unconstrained features , 2020, Sampling Theory, Signal Processing, and Data Analysis.
[6] Marc Niethammer,et al. Dissecting Supervised Constrastive Learning , 2021, ICML.
[7] Zhihui Zhu,et al. A Geometric Analysis of Neural Collapse with Unconstrained Features , 2021, NeurIPS.
[8] Samy Bengio,et al. Understanding deep learning (still) requires rethinking generalization , 2021, Commun. ACM.
[9] Hangfeng He,et al. Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training , 2021, Proceedings of the National Academy of Sciences.
[10] S. Mallat,et al. Separation and Concentration in Deep Networks , 2020, ICLR.
[11] On the emergence of simplex symmetry in the final and penultimate layers of neural network classifiers , 2020, 2012.05420.
[12] Mikhail Belkin,et al. Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks , 2020, ICLR.
[13] Mert Pilanci,et al. Revealing the Structure of Deep Neural Networks via Convex Duality , 2020, ICML.
[14] Vardan Papyan,et al. Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra , 2020, ArXiv.
[15] David L. Donoho,et al. Prevalence of neural collapse during the terminal phase of deep learning training , 2020, Proceedings of the National Academy of Sciences.
[16] Mikhail Belkin,et al. Does data interpolation contradict statistical optimality? , 2018, AISTATS.
[17] Sanjeev Arora,et al. On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization , 2018, ICML.
[18] Raef Bassily,et al. The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning , 2017, ICML.
[19] Elad Hoffer,et al. Train longer, generalize better: closing the generalization gap in large batch training of neural networks , 2017, NIPS.
[20] Joan Bruna,et al. Topology and Geometry of Half-Rectified Network Optimization , 2016, ICLR.
[21] Kilian Q. Weinberger,et al. Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[22] Kenji Kawaguchi,et al. Deep Learning without Poor Local Minima , 2016, NIPS.
[23] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[24] Andrew Zisserman,et al. Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.
[25] Geoffrey E. Hinton,et al. ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.
[26] R. Vershynin. How Close is the Sample Covariance Matrix to the Actual Covariance Matrix? , 2010, 1004.3484.
[27] Pablo A. Parrilo,et al. Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..
[28] Nathan Srebro,et al. Learning with matrix factorizations , 2004 .
[29] G. Watson. Characterization of the subdifferential of some matrix norms , 1992 .