Alternatives and similar repositories for lookahead

Users that are interested in lookahead are comparing it to the libraries listed below

• mgrankin / over9000

  View on GitHub
  Over9000 optimizer
  ☆424Nov 22, 2022Updated 3 years ago
• alphadl / lookahead.pytorch

  View on GitHub
  lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch
  ☆338Aug 9, 2019Updated 6 years ago
• lifeiteng / Optimizers

  View on GitHub
  Tensorflow Optimizers
  ☆11Sep 1, 2019Updated 6 years ago
• LiyuanLucasLiu / RAdam

  View on GitHub
  On the Variance of the Adaptive Learning Rate and Beyond
  ☆2,549Jul 31, 2021Updated 4 years ago
• BayesWatch / deficient-efficient

  View on GitHub
  Successfully training approximations to full-rank matrices for efficiency in deep learning.
  ☆17Jan 5, 2021Updated 5 years ago
• digantamisra98 / EvoNorm

  View on GitHub
  Unofficial PyTorch Implementation of EvoNorm
  ☆123Aug 29, 2021Updated 4 years ago
• gbaydin / hypergradient-descent

  View on GitHub
  Hypergradient descent
  ☆147May 31, 2024Updated last year
• ColinQiyangLi / LConvNet

  View on GitHub
  Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)
  ☆36Jun 25, 2020Updated 5 years ago
• jettify / pytorch-optimizer

  View on GitHub
  torch-optimizer -- collection of optimizers for Pytorch
  ☆3,161Mar 22, 2024Updated last year
• lessw2020 / Ranger-Deep-Learning-Optimizer

  View on GitHub
  Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
  ☆1,208Dec 22, 2023Updated 2 years ago
• lonePatient / lookahead_pytorch

  View on GitHub
  pytorch implement of Lookahead Optimizer
  ☆195Jun 20, 2022Updated 3 years ago
• timgaripov / dnn-mode-connectivity

  View on GitHub
  Mode Connectivity and Fast Geometric Ensembles in PyTorch
  ☆283Oct 24, 2022Updated 3 years ago
• clovaai / AdamP

  View on GitHub
  AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
  ☆415Jan 13, 2021Updated 5 years ago
• juntang-zhuang / Adabelief-Optimizer

  View on GitHub
  Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"
  ☆1,068Aug 9, 2024Updated last year
• PetrochukM / HParams

  View on GitHub
  Configure Python functions explicitly and safely
  ☆128Nov 18, 2024Updated last year
• christopher-beckham / amr

  View on GitHub
  Official adversarial mixup resynthesis repository
  ☆35Feb 14, 2020Updated 6 years ago
• taoyang1122 / GradAug

  View on GitHub
  [NeurIPS'20] GradAug: A New Regularization Method for Deep Neural Networks
  ☆94Dec 16, 2020Updated 5 years ago
• liamcli / randomNAS_release

  View on GitHub
  Code release for paper "Random Search and Reproducibility for NAS"
  ☆167Jul 1, 2019Updated 6 years ago
• arthurmensch / online_sinkhorn

  View on GitHub
  ☆14Sep 4, 2020Updated 5 years ago
• pedro-morgado / nettailor

  View on GitHub
  Source code accompanying our CVPR 2019 paper: "NetTailor: Tuning the architecture, not just the weights."
  ☆54Aug 14, 2021Updated 4 years ago
• facebookresearch / higher

  View on GitHub
  higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual tr…
  ☆1,627Mar 25, 2022Updated 3 years ago
• KordingLab / hilbert-constrained-gradient-descent

  View on GitHub
  Pytorch optimizers implementing Hilbert Constrained Gradient Descent
  ☆19May 9, 2019Updated 6 years ago
• Luolc / AdaBound

  View on GitHub
  An optimizer that trains as fast as Adam and as good as SGD.
  ☆2,913Jul 23, 2023Updated 2 years ago
• shyam671 / Twin_Auxiliary_Classifier_GAN

  View on GitHub
  Twin Auxiliary Classifiers GAN (NeurIPS 2019) [Spotlight]
  ☆15Sep 19, 2019Updated 6 years ago
• ZhiluZhang123 / neurips_2020_distillation

  View on GitHub
  Code for "Self-Distillation as Instance-Specific Label Smoothing"
  ☆16Oct 22, 2020Updated 5 years ago
• peterhj / shiftnet_cuda_v2

  View on GitHub
  ☆31Mar 29, 2018Updated 7 years ago
• zeke-xie / Positive-Negative-Momentum

  View on GitHub
  [ICML 2021] The official PyTorch Implementations of Positive-Negative Momentum Optimizers.
  ☆27Aug 30, 2022Updated 3 years ago
• maciejczyzewski / batchboost

  View on GitHub
  batchboost is a variation on MixUp that instead of mixing just two images, mixes many images together.
  ☆44Jan 26, 2020Updated 6 years ago
• kakaobrain / torchlars

  View on GitHub
  A LARS implementation in PyTorch
  ☆353Feb 21, 2020Updated 5 years ago
• ZHKKKe / DualStudent

  View on GitHub
  Code for Paper ''Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning'' [ICCV 2019]
  ☆119Aug 20, 2020Updated 5 years ago
• lucidrains / isab-pytorch

  View on GitHub
  An implementation of (Induced) Set Attention Block, from the Set Transformers paper
  ☆67Jan 10, 2023Updated 3 years ago
• facebookresearch / pycls

  View on GitHub
  Codebase for Image Classification Research, written in PyTorch.
  ☆2,169Mar 20, 2024Updated last year
• awwong1 / torchprof

  View on GitHub
  PyTorch layer-by-layer model profiler
  ☆607May 23, 2021Updated 4 years ago
• kakaobrain / fast-autoaugment

  View on GitHub
  Official Implementation of 'Fast AutoAugment' in PyTorch.
  ☆1,614Jun 16, 2021Updated 4 years ago
• timgaripov / swa

  View on GitHub
  Stochastic Weight Averaging in PyTorch
  ☆977Aug 1, 2021Updated 4 years ago
• BorealisAI / bre-gan

  View on GitHub
  Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · …
  ☆20Jun 12, 2018Updated 7 years ago
• pomonam / NoisyNaturalGradient

  View on GitHub
  TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".
  ☆60Jan 12, 2019Updated 7 years ago
• pytorch / contrib

  View on GitHub
  Implementations of ideas from recent papers
  ☆392Dec 22, 2020Updated 5 years ago
• zhang64-llnl / Mix-n-Match-Calibration

  View on GitHub
  ☆38Nov 13, 2020Updated 5 years ago