Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
暂无分享,去创建一个
Sanjeev Arora | Wei Hu | Rong Ge | Zhiyuan Li | Holden Lee | Xiang Wang | Yi Zhang | Rohith Kuditipudi | Sanjeev Arora | Rong Ge | Yi Zhang | Wei Hu | Holden Lee | Xiang Wang | Zhiyuan Li | Rohith Kuditipudi
[1] Suvrit Sra,et al. A Critical View of Global Optimality in Deep Learning , 2018, ArXiv.
[2] Quynh Nguyen,et al. On Connected Sublevel Sets in Deep Learning , 2019, ICML.
[3] Andrew Gordon Wilson,et al. Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs , 2018, NeurIPS.
[4] Yann LeCun,et al. The Loss Surfaces of Multilayer Networks , 2014, AISTATS.
[5] R. Srikant,et al. Understanding the Loss Surface of Neural Networks for Binary Classification , 2018, ICML.
[6] Matthew Botvinick,et al. On the importance of single directions for generalization , 2018, ICLR.
[7] Surya Ganguli,et al. Identifying and attacking the saddle point problem in high-dimensional non-convex optimization , 2014, NIPS.
[8] Andrew Zisserman,et al. Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.
[9] Ohad Shamir,et al. Spurious Local Minima are Common in Two-Layer ReLU Neural Networks , 2017, ICML.
[10] Richa Singh,et al. Guided Dropout , 2018, AAAI.
[11] Joel A. Tropp,et al. User-Friendly Tail Bounds for Sums of Random Matrices , 2010, Found. Comput. Math..
[12] Yi Zhang,et al. Stronger generalization bounds for deep nets via a compression approach , 2018, ICML.
[13] Suvrit Sra,et al. Small nonlinearities in activation functions create bad local minima in neural networks , 2018, ICLR.
[14] Joan Bruna,et al. Topology and Geometry of Half-Rectified Network Optimization , 2016, ICLR.
[15] Fred A. Hamprecht,et al. Essentially No Barriers in Neural Network Energy Landscape , 2018, ICML.
[16] Jonathan Tompson,et al. Efficient object localization using Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[17] Kenji Kawaguchi,et al. Deep Learning without Poor Local Minima , 2016, NIPS.
[18] Matthias Hein,et al. On the loss landscape of a class of deep neural networks with no bad local valleys , 2018, ICLR.
[19] Joan Bruna,et al. Spurious Valleys in Two-layer Neural Network Optimization Landscapes , 2018, 1802.06384.