Skip to content

Code for the paper "Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping"

Notifications You must be signed in to change notification settings

eduardgorbunov/accelerated_clipping

Repository files navigation

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

Code for the paper "Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping" by Eduard Gorbunov, Marina Danilova and Alexander Gasnikov, NeurIPS 2020

https://arxiv.org/pdf/2005.10785.pdf

To run the experiments one should download the data from LIBSVM https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html and save the datasets in .txt format in the folder called "datasets". Also one should create folders "dump" and "plot".

Use jupyter notebooks that we prepared in order to repeat/check our experiments.

algorithms.py -- file with implementation of methods

utils.py -- file with useful tools for saving results and making plots

functions.py -- file with implementation of oracles that we use

About

Code for the paper "Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published