7.8k citations · 21.1k across the 144 of their papers we have counts for
3 papers · 1 filter
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Yann Dauphin, Razvan Pascanu, Caglar Gulcehre +3
A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-New…
On the saddle point problem for non-convex optimization
Razvan Pascanu, Yann N. Dauphin, Surya Ganguli +1
A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-New…
On the Number of Linear Regions of Deep Neural Networks
Guido Montúfar, Razvan Pascanu, Kyunghyun Cho +1
We study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions th…