暂无分享,去创建一个
[1] Suvrit Sra,et al. Global optimality conditions for deep neural networks , 2017, ICLR.
[2] Li Zhang,et al. Depth creates no more spurious local minima , 2019, ArXiv.
[3] Andrew Gordon Wilson,et al. Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs , 2018, NeurIPS.
[4] Sanjeev Arora,et al. Implicit Regularization in Deep Matrix Factorization , 2019, NeurIPS.
[5] Andrea Montanari,et al. A mean field view of the landscape of two-layer neural networks , 2018, Proceedings of the National Academy of Sciences.
[6] Suvrit Sra,et al. Small nonlinearities in activation functions create bad local minima in neural networks , 2018, ICLR.
[7] Rekha R. Thomas,et al. The Euclidean Distance Degree of an Algebraic Variety , 2013, Foundations of Computational Mathematics.
[8] Wei Hu,et al. A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks , 2018, ICLR.
[9] Francis Bach,et al. On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport , 2018, NeurIPS.
[10] Luke Oeding,et al. Learning Algebraic Models of Quantum Entanglement , 2019, Quantum Inf. Process..
[11] F. Opitz. Information geometry and its applications , 2012, 2012 9th European Radar Conference.
[12] Tengyu Ma,et al. Identity Matters in Deep Learning , 2016, ICLR.
[13] Thomas Laurent,et al. Deep linear neural networks with arbitrary loss: All local minima are global , 2017, ArXiv.
[14] Joan Bruna,et al. Spurious Valleys in Two-layer Neural Network Optimization Landscapes , 2018, 1802.06384.
[15] Bernd Sturmfels,et al. Exact Solutions in Structured Low-Rank Approximation , 2013, SIAM J. Matrix Anal. Appl..
[16] Kenji Kawaguchi,et al. Deep Learning without Poor Local Minima , 2016, NIPS.
[17] Tingting Tang,et al. The Loss Surface of Deep Linear Networks Viewed Through the Algebraic Geometry Lens , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.
[18] Yann LeCun,et al. The Loss Surfaces of Multilayer Networks , 2014, AISTATS.
[19] Holger Rauhut,et al. Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers , 2019, ArXiv.
[20] Yi Zhou,et al. Critical Points of Neural Networks: Analytical Forms and Landscape Properties , 2017, ArXiv.
[21] J. Draisma,et al. The average number of critical rank-one approximations to a tensor , 2014, 1408.3507.
[22] Haihao Lu,et al. Depth Creates No Bad Local Minima , 2017, ArXiv.
[23] John M. Lee. Introduction to Smooth Manifolds , 2002 .
[24] Joan Bruna,et al. On the Expressive Power of Deep Polynomial Neural Networks , 2019, NeurIPS.
[25] Kurt Hornik,et al. Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.
[26] Joe W. Harris,et al. Algebraic Geometry: A First Course , 1995 .