SIAMJO
2008
13 years 11 months ago
2008
We show that the optimal complexity of Nesterov's smooth first-order optimization algorithm is preserved when the gradient is only computed up to a small, uniformly bounded er...
ESANN
2001
14 years 27 days ago
2001
Neural networks use neurons of the same type in each layer but such architecture cannot lead to data models of optimal complexity and accuracy. Networks with architectures (number ...