neuralnut / tf_optimizers Goto Github PK

Optimizers in tensorflow from scratch. See example.py and optimizers.py.

Optimizers

• Stochastic Gradient descent
• Stochastic Gradient descent with gradient clipping
• Momentum
• Nesterov momentum
• Adagrad
• Adadelta
• RMSProp
• Adam
• Adamax
• SMORMS3

• An overview of gradient descent optimization algorithms: http://sebastianruder.com/optimizing-gradient-descent/
• Chainer Optimizers: http://docs.chainer.org/en/stable/reference/optimizers.html
• SMORMS3: http://sifter.org/~simon/journal/20150420.html
• AdaGrad, RMSProp, AdaDelta, Adam, SMORMS3 (in japanese): http://qiita.com/skitaoka/items/e6afbe238cd69c899b2a