Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Fast mean estimation and outlier detection

This repo contains code for our paper Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection.

Yihe Dong, Sam Hopkins, Jerry Li


Install

To install dependencies, run:

pip install -r requirements.txt

Description of select scripts:

  • mean.py contains the backbone of the experimental setup and evaluation.
  • utils.py contains various utilities methods, such as fast JL computation.
  • Auxiliary scripts specific to certain experiments: pixel.py used for running the hot pixels experiments on CIFAR data, words.py used when running word embeddings experiments.

The data directory contains select data for running the experiments. Additional data should be downloaded into the data directory: GloVe embeddings can be downloaded here. CIFAR images can be downloaded from here.

The main script mean.py with appropriate arguments. For instance, to run experiments on synthetic data with respect to varying alpha:

python mean.py --experiment_type syn_lamb

And the same on word embeddings data:

python mean.py --experiment_type text_lamb

To run experiments on CIFAR images:

python pixel.py --experiment_type image_lamb

For more available runtime options see:

python mean.py -h

Reference

If you find our paper and repo useful, please cite as:

@inproceedings{que2019,
  title={Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection},
  author={Dong, Yihe and Hopkins, Samuel and Li, Jerry},
  booktitle={Advances in Neural Information Processing Systems},
  year={2019}
}

About

[NeurIPS 2019 Spotlight] High dimensional mean estimation and outlier detection in nearly-linear time.

Resources

Releases

No releases published

Packages

No packages published

Languages