v1v2v3 (latest)

To understand deep learning we need to understand kernel learning

5 February 2018

Papers citing "To understand deep learning we need to understand kernel learning"

21 / 271 papers shown

Title
Reconciling modern machine learning practice and the bias-variance trade-off M. Belkin Daniel J. Hsu Siyuan Ma Soumik Mandal 305 1,665 0 28 Dec 2018
A Differential Topological View of Challenges in Learning with Feedforward Neural Networks Hao Shen AAML AI4CE 69 6 0 26 Nov 2018
Minimum weight norm models do not always generalize well for over-parameterized problems Vatsal Shah Anastasios Kyrillidis Sujay Sanghavi 105 21 0 16 Nov 2018
Accelerating SGD with momentum for over-parameterized learning Chaoyue Liu M. Belkin ODL 110 19 0 31 Oct 2018
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel Colin Wei Jason D. Lee Qiang Liu Tengyu Ma 268 245 0 12 Oct 2018
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning Charles H. Martin Michael W. Mahoney AI4CE 137 201 0 02 Oct 2018
Gradient and Newton Boosting for Classification and Regression Fabio Sigrist 89 62 0 09 Aug 2018
Just Interpolate: Kernel "Ridgeless" Regression Can Generalize Tengyuan Liang Alexander Rakhlin 99 355 0 01 Aug 2018
Theory IIIb: Generalization in Deep Networks T. Poggio Q. Liao Brando Miranda Andrzej Banburski Xavier Boix Jack Hidary ODL AI4CE 104 26 0 29 Jun 2018
Neural Tangent Kernel: Convergence and Generalization in Neural Networks Arthur Jacot Franck Gabriel Clément Hongler 376 3,226 0 20 Jun 2018
Kernel machines that adapt to GPUs for effective large batch training Siyuan Ma M. Belkin 22 2 0 15 Jun 2018
Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate M. Belkin Daniel J. Hsu P. Mitra AI4CE 164 259 0 13 Jun 2018
Chaining Mutual Information and Tightening Generalization Bounds Amir-Reza Asadi Emmanuel Abbe S. Verdú AI4CE 62 124 0 11 Jun 2018
Minnorm training: an algorithm for training over-parameterized deep neural networks Yamini Bansal Madhu S. Advani David D. Cox Andrew M. Saxe ODL 81 18 0 03 Jun 2018
Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization D. Kobak Jonathan Lomond Benoit Sanchez 94 89 0 28 May 2018
Deep learning generalizes because the parameter-function map is biased towards simple functions Guillermo Valle Pérez Chico Q. Camargo A. Louis MLT AI4CE 122 232 0 22 May 2018
Fast Convergence for Stochastic and Distributed Gradient Descent in the Interpolation Limit P. Mitra 21 4 0 08 Mar 2018
Learning Integral Representations of Gaussian Processes Zilong Tan S. Mukherjee GP 67 2 0 21 Feb 2018
An analysis of training and generalization errors in shallow and deep networks H. Mhaskar T. Poggio UQCV 57 18 0 17 Feb 2018
Approximation beats concentration? An approximation view on inference with smooth radial kernels M. Belkin 125 70 0 10 Jan 2018
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning Siyuan Ma Raef Bassily M. Belkin 117 291 0 18 Dec 2017