torch-optimizer 0.0.1a3

Simple example

import torch_optimizer as optim

# model = ...
optimizer = optim.DiffGrad(model.parameters(), lr=0.001)
optimizer.step()

Installation

Installation process is simple, just:

$ pip install torch_optimizer

AccSGD

import torch_optimizer as optim

# model = ...
optimizer = optim.AccSGD(
    model.parameters(),
    lr=1e-3,
    kappa=1000.0,
    xi=10.0,
    small_const=0.7,
    weight_decay=0
)
optimizer.step()

Paper: On the insufficiency of existing momentum schemes for Stochastic Optimization (2019) [https://arxiv.org/abs/1803.05591]

Reference Code: https://github.com/rahulkidambi/AccSGD

AdaBound

import torch_optimizer as optim

# model = ...
optimizer = optim.AdaBound(
    m.parameters(),
    lr= 1e-3,
    betas= (0.9, 0.999),
    final_lr = 0.1,
    gamma=1e-3,
    eps= 1e-8,
    weight_decay=0,
    amsbound=False,
)
optimizer.step()

Paper: Adaptive Gradient Methods with Dynamic Bound of Learning Rate (2019) [https://arxiv.org/abs/1902.09843]

Reference Code: https://github.com/Luolc/AdaBound

AdaMod

AdaMod method restricts the adaptive learning rates with adaptive and momental upper bounds. The dynamic learning rate bounds are based on the exponential moving averages of the adaptive learning rates themselves, which smooth out unexpected large learning rates and stabilize the training of deep neural networks.

import torch_optimizer as optim

# model = ...
optimizer = optim.AdaMod(
    m.parameters(),
    lr= 1e-3,
    betas=(0.9, 0.999),
    beta3=0.999,
    eps=1e-8,
    weight_decay=0,
)
optimizer.step()

Paper: An Adaptive and Momental Bound Method for Stochastic Learning. (2019) [https://arxiv.org/abs/1910.12249v1]

Reference Code: https://github.com/lancopku/AdaMod

DiffGrad

Optimizer based on the difference between the present and the immediate past gradient, the step size is adjusted for each parameter in such a way that it should have a larger step size for faster gradient changing parameters and a lower step size for lower gradient changing parameters.

import torch_optimizer as optim

# model = ...
optimizer = optim.DiffGrad(
    m.parameters(),
    lr= 1e-3,
    betas=(0.9, 0.999),
    eps=1e-8,
    weight_decay=0,
)
optimizer.step()

Paper: diffGrad: An Optimization Method for Convolutional Neural Networks. (2019) [https://arxiv.org/abs/1909.11015]

Reference Code: https://github.com/shivram1987/diffGrad

Lamb

import torch_optimizer as optim

# model = ...
optimizer = optim.Lamb(
    m.parameters(),
    lr= 1e-3,
    betas=(0.9, 0.999),
    eps=1e-8,
    weight_decay=0,
)
optimizer.step()

Paper: Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (2019) [https://arxiv.org/abs/1904.00962]

Reference Code: https://github.com/cybertronai/pytorch-lamb

RAdam

import torch_optimizer as optim

# model = ...
optimizer = optim.RAdam(
    m.parameters(),
    lr= 1e-3,
    betas=(0.9, 0.999),
    eps=1e-8,
    weight_decay=0,
)
optimizer.step()

Paper: On the Variance of the Adaptive Learning Rate and Beyond (2019) [https://arxiv.org/abs/1908.03265]

Reference Code: https://github.com/LiyuanLucasLiu/RAdam

SGDW

import torch_optimizer as optim

# model = ...
optimizer = optim.SGDW(
    m.parameters(),
    lr= 1e-3,
    momentum=0,
    dampening=0,
    weight_decay=1e-2,
    nesterov=False,
)
optimizer.step()

Paper: SGDR: Stochastic Gradient Descent with Warm Restarts (2017) [https://arxiv.org/abs/1904.00962]

Reference Code: https://arxiv.org/abs/1608.03983

Yogi

Yogi is optimization algorithm based on ADAM with more fine grained effective learning rate control, and has similar theoretical guarantees on convergence as ADAM.

import torch_optimizer as optim

# model = ...
optimizer = optim.Yogi(
    m.parameters(),
    lr= 1e-3,
    betas=(0.9, 0.999),
    eps=1e-8,
    weight_decay=0,
)
optimizer.step()

Paper: Adaptive Methods for Nonconvex Optimization (2018) [https://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization]

Reference Code: https://github.com/4rtemi5/Yogi-Optimizer_Keras

Changes

0.0.1 (YYYY-MM-DD)

• Initial release.