Convergence of Gradient Descent on Separable Data
暂无分享,去创建一个
Nathan Srebro | Daniel Soudry | Jason D. Lee | Suriya Gunasekar | Mor Shpigel Nacson | Nathan Srebro | Suriya Gunasekar | Daniel Soudry | J. Lee | N. Srebro | M. S. Nacson
[1] Nathan Srebro,et al. Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate , 2018, AISTATS.
[2] Nikos Komodakis,et al. Wide Residual Networks , 2016, BMVC.
[3] Matus Telgarsky,et al. Margins, Shrinkage, and Boosting , 2013, ICML.
[4] Matus Telgarsky,et al. Risk and parameter convergence of logistic regression , 2018, ArXiv.
[5] Nathan Srebro,et al. Implicit Bias of Gradient Descent on Linear Convolutional Networks , 2018, NeurIPS.
[6] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .
[7] Nathan Srebro,et al. The Implicit Bias of Gradient Descent on Separable Data , 2017, J. Mach. Learn. Res..
[8] Kfir Y. Levy,et al. The Power of Normalization: Faster Evasion of Saddle Points , 2016, ArXiv.
[9] Nathan Srebro,et al. Characterizing Implicit Bias in Terms of Optimization Geometry , 2018, ICML.
[10] David P. Woodruff,et al. Sublinear Optimization for Machine Learning , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.
[11] Yi Zhou,et al. Convergence of SGD in Learning ReLU Models with Separable Data , 2018, ArXiv.
[12] Elad Hoffer,et al. Train longer, generalize better: closing the generalization gap in large batch training of neural networks , 2017, NIPS.
[13] Yi Zhou,et al. When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models? , 2018 .
[14] Samy Bengio,et al. Understanding deep learning requires rethinking generalization , 2016, ICLR.
[15] Ji Zhu,et al. Margin Maximizing Loss Functions , 2003, NIPS.
[16] Alex M. Andrew,et al. Boosting: Foundations and Algorithms , 2012 .
[17] Ryota Tomioka,et al. In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning , 2014, ICLR.
[18] Matus Telgarsky,et al. Gradient descent aligns the layers of deep linear networks , 2018, ICLR.