Linear Learning: Landscapes and Algorithms

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning without Poor Local Minima (2016, methodology): “An informal discussion of Conjecture 2.2 can be found in (Baldi, 1989).”
An empirical analysis of the optimization of deep network loss surfaces (2016, background): “a? 2 RELATED WORK 2.1 LOSS SURFACES There have been several attempts to understand the loss surfaces of deep neural networks. Some have studied the critical points of the deep linear neural networks (Baldi, 1989; Baldi & Hornik, Work done during an internship at Janelia Research Campus 1 arXiv:1”
Exponentially vanishing sub-optimal local minima in multilayer neural networks (2017, methodology): “, 2015; Kawaguchi, 2016) replaced the units (activation functions) with independent random variables; (Pennington & Bahri, 2017) replaces the weights and error residuals with independent random variables; (Baldi, 1989; Saxe et al., 2014; Hardt & Ma, 2017; Lu & Kawaguchi, 2017; Zhou & Feng, 2017) use”
An Empirical Analysis of Deep Network Loss Surfaces (2016, background): “Some have studied the critical points of the deep linear neural networks (Baldi, 1989; Baldi & Hornik, * Work done during an internship at Janelia Research Campus 1989; Baldi & Lu, 2012).”
Depth Creates No Bad Local Minima (2017, unknown): “Theorem 2.3 generalizes the second statement with fewer assumptions; the previous papers (Baldi, 1989; Kawaguchi, 2016) assume that the data matrix Y X T ( XX T ) − 1 XY T has distinct eigenvalues, whereas we do not assume that.”