https://github.com/airoldilab/ai-sgd

Towards stability and optimality in stochastic gradient descent
https://github.com/airoldilab/ai-sgd

Last synced: about 2 months ago
JSON representation

Towards stability and optimality in stochastic gradient descent

• Host: GitHub
• URL: https://github.com/airoldilab/ai-sgd
• Owner: airoldilab
• Created: 2014-12-06T23:35:35.000Z (about 10 years ago)
• Default Branch: master
• Last Pushed: 2015-05-21T20:30:25.000Z (over 9 years ago)
• Last Synced: 2024-03-27T12:18:03.817Z (9 months ago)
• Language: R
• Homepage:
• Size: 656 KB
• Stars: 5
• Watchers: 8
• Forks: 2
• Open Issues: 9
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Stability and optimality in stochastic gradient descent

This is the accompanying code implementation of the methods and algorithms

for a paper in progress.

## Maintainer

* Dustin Tran \

## References

* Francis Bach and Eric Moulines. Non-strongly-convex smooth stochastic

  approximation with convergence rate O(1/n). *Advances in Neural Information

  Processing Systems*, 2013.

* Jerome Friedman, Trevor Hastie, and Robert Tibshirani. Regularization paths

  for generalized linear models via coordinate descent. *Journal of Statistical

  Software*, 33(1):1-22, 2010.

* Rie Johnson and Tong Zhang. Accelerating stochastic gradient descent using

  predictive variance reduction. *Advances in Neural Information Processing

  Systems*, 2013.

* David Ruppert. Efficient estimations from a slowly convergent robbins-monro

  process. Technical report, Cornell University Operations Research and

  Industrial Engineering, 1988.

* Wei Xu. Towards optimal one pass large scale learning with averaged stochastic

  gradient descent. *arXiv preprint

  [arXiv:1107.2490](http://arxiv.org/abs/1107.2490)*, 2011.