Abstract
Finding minima of a real valued non-convex function over a high dimensional space is a major challenge in science. We provide evidence that some such functions that are defined on high dimensional domains have a narrow band of values whose pre-image contains the bulk of its critical points. This is in contrast with the low dimensional picture in which this band is wide. Our simulations agree with the previous theoretical work on spin glasses that proves the existence of such a band when the dimension of the domain tends to infinity. Furthermore our experiments on teacher-student networks with the MNIST dataset establish a similar phenomenon in deep networks. We finally observe that both the gradient descent and the stochastic gradient descent methods can reach this level within the same number of steps.
Original language | English (US) |
---|---|
State | Published - Jan 1 2015 |
Event | 3rd International Conference on Learning Representations, ICLR 2015 - San Diego, United States Duration: May 7 2015 → May 9 2015 |
Conference
Conference | 3rd International Conference on Learning Representations, ICLR 2015 |
---|---|
Country/Territory | United States |
City | San Diego |
Period | 5/7/15 → 5/9/15 |
ASJC Scopus subject areas
- Education
- Linguistics and Language
- Language and Linguistics
- Computer Science Applications