L2L
L2L copied to clipboard
Implement functions with saddle points in high dimensions
How do we construct such functions? (references)
Pascanu, Razvan, et al. "On the saddle point problem for non-convex optimization." arXiv preprint arXiv:1405.4604 (2014). and Dauphin, Yann N., et al. "Identifying and attacking the saddle point problem in high-dimensional non-convex optimization." Advances in neural information processing systems. 2014. might contain some relevant details.