https://github.com/shreypandit/lipschitz_adaptive_learning_rate

https://github.com/shreypandit/lipschitz_adaptive_learning_rate

Last synced: about 1 year ago
JSON representation

• Host: GitHub
• URL: https://github.com/shreypandit/lipschitz_adaptive_learning_rate
• Owner: ShreyPandit
• Created: 2020-06-15T05:30:45.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2020-08-05T07:23:32.000Z (almost 6 years ago)
• Last Synced: 2025-02-08T18:13:58.492Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 10.1 MB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Lipschitz Adaptive Learning Rate




This is an implemetation of paper by:- 


Yedida, Rahul, and Snehanshu Saha. "A novel adaptive learning rate scheduler for deep neural networks." arXiv preprint arXiv:1902.07399 (2019).




Using keras and Tensorflow . Main function is lr_scheduler which uses the callback of LRScheduler. All the code can be found in this repository.




The research paper that has been implemented is also uploaded 


The summary sheet is made which contains the result for all of the datasets.


The datasets on which this LALR is implemented are:-




  
MNIST 

  
IRIS 

  
Boston Housing data 

  
CIFAR-10 

  
CIFAR-100 



# Setup Requirements 




The code uses the following packages that must be installed 




  
Keras

  
Tensoflow

  
SKLearn

  
Numpy 

  
Matplotlib

  
TQDM



# Citation

If you find the following work useful please cite the paper-


@article{yedida2019novel,

  title={A novel adaptive learning rate scheduler for deep neural networks},

  author={Yedida, Rahul and Saha, Snehanshu},

  journal={arXiv preprint arXiv:1902.07399},

  year={2019}

}