112 citations · 288 across the 11 of their papers we have counts for
Showing 2017Show all
3 papers · 1 filter
cs.LG2017★ 112 cited
Learning One-hidden-layer Neural Networks with Landscape Design
Rong Ge, Jason D. Lee, Tengyu Ma
We consider the problem of learning a one-hidden-layer neural network: we assume the input is from Gaussian distribution and the label , w…
stat.ML2017★ 76 cited
First-order Methods Almost Always Avoid Saddle Points
Jason D. Lee, Ioannis Panageas, Georgios Piliouras +3
We establish that first-order methods avoid saddle points for almost all initializations. Our results apply to a wide variety of first-order methods, including gradient descent, bl…
math.OC2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points
Simon S. Du, Chi Jin, Jason D. Lee +3
Although gradient descent (GD) almost always escapes saddle points asymptotically [Lee et al., 2016], this paper shows that even with fairly natural random initialization schemes a…