201419/Optimizer-PyTorch

Package of Optimizer implemented with PyTorch .

Optimizer-PyTorch

Package of Optimizer implemented with PyTorch .

Optimizer Lists

SGD: stochastic gradient descent

• https://github.com/pytorch/pytorch/blob/master/torch/optim/sgd.py

Adam: A Method for Stochastic Optimization

• https://arxiv.org/abs/1412.6980
• https://openreview.net/forum?id=ryQu7f-RZ
• https://github.com/pytorch/pytorch/blob/master/torch/optim/adam.py

Adabound: Adaptive Gradient Methods with Dynamic Bound of Learning Rate

• https://arxiv.org/abs/1902.09843
• https://openreview.net/forum?id=Bkg3g2R9FX
• https://github.com/Luolc/AdaBound

RAdam: On the Variance of the Adaptive Learning Rate and Beyond

• https://arxiv.org/abs/1908.03265
• https://github.com/LiyuanLucasLiu/RAdam

Lookahead: Lookahead Optimizer: k steps forward, 1 step back

• https://arxiv.org/abs/1907.08610

Optimistic

• https://github.com/bruno-31/diff-game/blob/master/optimizers.py

OptimAdam

• https://github.com/kojino/GAN-Convergence/blob/master/script/optimizer.py

OMD

• https://github.com/GauthierGidel/Variational-Inequality-GAN/blob/master/optim/omd.py

ExtraGradient

• https://github.com/GauthierGidel/Variational-Inequality-GAN/blob/master/optim/extragradient.py

STORM: STOchastic Recursive Momentum

• < Momentum-Based Variance Reduction in Non-Convex SGD >
• http://papers.nips.cc/paper/9659-momentum-based-variance-reduction-in-non-convex-sgd
• https://github.com/google-research/google-research/blob/master/storm_optimizer/storm_optimizer.py (TensorFlow)

Others

• https://ruder.io/optimizing-gradient-descent/index.html
• https://github.com/lifeiteng/Optimizers
• http://stanford.edu/~boyd/
• http://www.athenasc.com/nonlinbook.html