Fetching the paper…
Reading the bibliography…
Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the first-order information.
Estimating the largest eigenvalue by the power and lanczos algorithms with a random start
J. Kuczynski and H. Wozniakowski · 1992
Earlier work this paper cites.
Introductory lectures on convex optimization : a basic course
Yurii Nesterov · 2004
Earlier work this paper cites.
Cubic regularization of newton method and its global performance
Yurii Nesterov and Boris T Polyak · 2006
Earlier work this paper cites.
Deep learning via hessian-free optimization
James Martens · 2010
Earlier work this paper cites.
Stochastic first- and zeroth-order methods for nonconvex stochastic programming
Saeed Ghadimi and Guanghui Lan · 2013
Earlier work this paper cites.
The noisy power method: A meta algorithm with applications
Moritz Hardt and Eric Price · 2014
Earlier work this paper cites.
Escaping from saddle points — online stochastic gradient for tensor decomposition
Rong Ge, Furong Huang, Chi Jin, and Yang Yuan · 2015
Earlier work this paper cites.
Accelerated proximal gradient methods for nonconvex programming
Huan Li and Zhouchen Lin · 2015
Earlier work this paper cites.
An improved gap-dependency analysis of the noisy power method
Maria-Florina Balcan, Simon Shaolei Du, Yining Wang, and Adams Wei Yu · 2016
Earlier work this paper cites.
Accelerated methods for non-convex optimization
Yair Carmon, John C. Duchi, Oliver Hinder, and Aaron Sidford · 2016
Cited alongside, same era.
Accelerated gradient methods for nonconvex nonlinear and stochastic programming
Saeed Ghadimi and Guanghui Lan · 2016
Cited alongside, same era.
Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
Saeed Ghadimi, Guanghui Lan, and Hongchao Zhang · 2016
Cited alongside, same era.
Deep learning
Ian Goodfellow, Yoshua Bengio, and Aaron Courville · 2016
Cited alongside, same era.
On graduated optimization for stochastic non-convex problems
Elad Hazan, Kfir Yehuda Levy, and Shai Shalev-Shwartz · 2016
Cited alongside, same era.
”convex until proven guilty”: Dimension-free acceleration of gradient descent on non-convex functions
Yair Carmon, John C. Duchi, Oliver Hinder, and Aaron Sidford · 2017
Closest in time.
Sub-sampled cubic regularization for non-convex optimization
Jonas Moritz Kohler and Aurélien Lucchi · 2017
Closest in time.
Non-convex finite-sum optimization via SCSG methods
Lihua Lei, Cheng Ju, Jianbo Chen, and Michael I Jordan · 2017
Closest in time.
Behavior of accelerated gradient methods near critical points of nonconvex problems
Michael O’Neill and Stephen J. Wright · 2017
Closest in time.
A generic approach for escaping saddle points
Sashank J Reddi, Manzil Zaheer, Suvrit Sra, Barnabas Poczos, Francis Bach, Ruslan Salakhutdinov, and Alexander J Smola · 2017
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Kfir Y. Levy · 2016
Cited alongside, same era.
Unified convergence analysis of stochastic momentum methods for convex and non-convex optimization
Tianbao Yang, Qihang Lin, and Zhe Li · 2016
Cited alongside, same era.
Finding approximate local minima faster than gradient descent
Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan, and Tengyu Ma · 2017
Cited alongside, same era.
Natasha 2: Faster non-convex optimization than sgd
Zeyuan Allen-Zhu · 2017
Cited alongside, same era.
Adaptive cubic regularisation methods for unconstrained optimization. part i: motivation, convergence and numerical results
Coralia Cartis, Nicholas I. M. Gould, and Philippe L. Toint
Cited in the paper.
Adaptive cubic regularisation methods for unconstrained optimization. part ii: worst-case function- and derivative-evaluation complexity
Coralia Cartis, Nicholas I. M. Gould, and Philippe L. Toint
Cited in the paper.
How to escape saddle points efficiently
Chi Jin, Rong Ge, Praneeth Netrapalli, Sham M Kakade, and Michael I Jordan
Cited in the paper.
Clement W. Royer and Stephen J. Wright · 2017
Closest in time.
Newton-type methods for non-convex optimization under inexact hessian information
Peng Xu, Farbod Roosta-Khorasani, and Michael W. Mahoney · 2017
Closest in time.
A hitting time analysis of stochastic gradient langevin dynamics
Yuchen Zhang, Percy Liang, and Moses Charikar · 2017
Closest in time.