Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
1812.04754
Cited By
Gradient Descent Happens in a Tiny Subspace
12 December 2018
Guy Gur-Ari
Daniel A. Roberts
Ethan Dyer
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Gradient Descent Happens in a Tiny Subspace"
13 / 163 papers shown
Title
Quantum algorithm for finding the negative curvature direction in non-convex optimization
Kaining Zhang
Min-hsiu Hsieh
Liu Liu
Dacheng Tao
11
3
0
17 Sep 2019
Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
Xinyan Li
Qilong Gu
Yingxue Zhou
Tiancong Chen
A. Banerjee
ODL
26
51
0
24 Jul 2019
Subspace Inference for Bayesian Deep Learning
Pavel Izmailov
Wesley J. Maddox
Polina Kirichenko
T. Garipov
Dmitry Vetrov
A. Wilson
UQCV
BDL
30
142
0
17 Jul 2019
SGD momentum optimizer with step estimation by online parabola model
J. Duda
ODL
13
22
0
16 Jul 2019
Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
Mingchen Li
Mahdi Soltanolkotabi
Samet Oymak
NoLa
28
351
0
27 Mar 2019
A Simple Baseline for Bayesian Uncertainty in Deep Learning
Wesley J. Maddox
T. Garipov
Pavel Izmailov
Dmitry Vetrov
A. Wilson
BDL
UQCV
28
793
0
07 Feb 2019
Negative eigenvalues of the Hessian in deep neural networks
Guillaume Alain
Nicolas Le Roux
Pierre-Antoine Manzagol
11
42
0
06 Feb 2019
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directions
J. Duda
ODL
4
1
0
31 Jan 2019
An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
Behrooz Ghorbani
Shankar Krishnan
Ying Xiao
ODL
16
313
0
29 Jan 2019
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
V. Papyan
11
86
0
24 Jan 2019
An Empirical Model of Large-Batch Training
Sam McCandlish
Jared Kaplan
Dario Amodei
OpenAI Dota Team
13
267
0
14 Dec 2018
A Modern Take on the Bias-Variance Tradeoff in Neural Networks
Brady Neal
Sarthak Mittal
A. Baratin
Vinayak Tantia
Matthew Scicluna
Simon Lacoste-Julien
Ioannis Mitliagkas
29
167
0
19 Oct 2018
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
Ben Athiwaratkun
Marc Finzi
Pavel Izmailov
A. Wilson
199
243
0
14 Jun 2018
Previous
1
2
3
4