Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations

26 December 2017

Papers citing "Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations"

10 / 10 papers shown

Title
Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin Colin Wei Tengyu Ma AAML OOD 36 85 0 09 Oct 2019
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks Yu Bai J. Lee 24 116 0 03 Oct 2019
On the Power and Limitations of Random Features for Understanding Neural Networks Gilad Yehudai Ohad Shamir MLT 26 181 0 01 Apr 2019
Deep Geometric Prior for Surface Reconstruction Francis Williams T. Schneider Claudio Silva Denis Zorin Joan Bruna Daniele Panozzo 3DPC 19 190 0 27 Nov 2018
Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications Deren Lei Zichen Sun Yijun Xiao William Yang Wang 33 14 0 01 Nov 2018
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem Alon Brutzkus Amir Globerson MLT 11 7 0 06 Oct 2018
Provably convergent acceleration in factored gradient descent with applications in matrix sensing Tayo Ajayi David Mildebrath Anastasios Kyrillidis Shashanka Ubaru Georgios Kollias K. Bouchard 18 1 0 01 Jun 2018
Characterizing Implicit Bias in Terms of Optimization Geometry Suriya Gunasekar Jason D. Lee Daniel Soudry Nathan Srebro AI4CE 37 399 0 22 Feb 2018
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks Mahdi Soltanolkotabi Adel Javanmard J. Lee 36 415 0 16 Jul 2017
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 308 2,890 0 15 Sep 2016