23 citations · 50 across the 6 of their papers we have counts for
4 papers · 1 filter
Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow
S. Indrapriyadarsini, Shahrzad Mahboubi, Hiroshi Ninomiya +1
Recent studies incorporate Nesterov's accelerated gradient method for the acceleration of gradient based training. The Nesterov's Accelerated Quasi-Newton (NAQ) method has shown to…
A Stochastic Variance Reduced Nesterov's Accelerated Quasi-Newton Method
Sota Yasuda, Shahrzad Mahboubi, S. Indrapriyadarsini +2
Recently algorithms incorporating second order curvature information have become popular in training neural networks. The Nesterov's Accelerated Quasi-Newton (NAQ) method has shown…
A Stochastic Quasi-Newton Method with Nesterov's Accelerated Gradient
S. Indrapriyadarsini, Shahrzad Mahboubi, Hiroshi Ninomiya +1
Incorporating second order curvature information in gradient based methods have shown to improve convergence drastically despite its computational intensity. In this paper, we prop…
An Adaptive Stochastic Nesterov Accelerated Quasi Newton Method for Training RNNs
S. Indrapriyadarsini, Shahrzad Mahboubi, Hiroshi Ninomiya +1
A common problem in training neural networks is the vanishing and/or exploding gradient problem which is more prominently seen in training of Recurrent Neural Networks (RNNs). Thus…