optimizer

Type Members

1. class AdaDelta extends Optimizer

   

   AdaDelta optimizer as described in Matthew D.

   AdaDelta optimizer as described in Matthew D. Zeiler, 2012. http://arxiv.org/abs/1212.5701

2. class AdaGrad extends Optimizer

   

   AdaGrad optimizer as described in Matthew D.

   AdaGrad optimizer as described in Matthew D. Zeiler, 2012. http://arxiv.org/pdf/1212.5701v1.pdf

3. class Adam extends Optimizer

   

   Adam optimizer as described in [King2014]

   Adam optimizer as described in [King2014]

   [King2014] Diederik Kingma, Jimmy Ba, Adam: A Method for Stochastic Optimization, http://arxiv.org/abs/1412.6980

4. class DCASGD extends Optimizer

   

   DCASGD optimizer with momentum and weight regularization.

   DCASGD optimizer with momentum and weight regularization. Implementation of paper "Asynchronous Stochastic Gradient Descent with Delay Compensation for Distributed Deep Learning"

5. class NAG extends Optimizer

   

   SGD with nesterov.

   SGD with nesterov. It is implemented according to https://github.com/torch/optim/blob/master/sgd.lua

6. class RMSProp extends Optimizer

   

   RMSProp optimizer as described in Tieleman & Hinton, 2012.

   RMSProp optimizer as described in Tieleman & Hinton, 2012. http://arxiv.org/pdf/1308.0850v5.pdf Eq(38) - Eq(45) by Alex Graves, 2013.

7. class SGD extends Optimizer

   

   A very simple SGD optimizer with momentum and weight regularization.

8. class SGLD extends Optimizer

   

   Stochastic Langevin Dynamics Updater to sample from a distribution.