gd-takes-the-shortest-path-exp-implementation
Implementation of the experiment mentioned in "Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?" paper by Samet Oymak and Mahdi Soltanolkotabi using PyTorch
https://github.com/umityigitbsrn/gd-takes-the-shortest-path-exp-implementation
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (3.4%) to scientific vocabulary
Repository
Implementation of the experiment mentioned in "Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?" paper by Samet Oymak and Mahdi Soltanolkotabi using PyTorch
Basic Info
- Host: GitHub
- Owner: umityigitbsrn
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Size: 1.18 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Implementation of the experiment mentioned in "Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?" paper by Samet Oymak and Mahdi Soltanolkotabi using PyTorch
MNIST Experiment
Implementation of this experiment is under 'mnist_experiment' folder
The experiment setup is taken from the page 12-13 (under 6.2 MNIST Experiment)
To save the resulting JSON files 'misfitdistance500json', 'misfitdistance5000json' folders need to be created
Low-rank Regression
Implementation of this experiment is under 'lowrankregression' folder
Gradient for the loss function of low rank regression can be mentioned in the paper on page 32 (in Appendix). The implementation will be based on this notation
The experiment setup is taken from the page 13 (under 6.2 Low-rank Regression)
To save the resulting JSON files 'misfitdistancejson' folder need to be created
Owner
- Name: Ümit Yiğit Başaran
- Login: umityigitbsrn
- Kind: user
- Location: Riverside, CA
- Repositories: 13
- Profile: https://github.com/umityigitbsrn
Citation (CITATION.cff)
preferred-citation:
type: article
authors:
- family-names: "Samet"
given-names: "Oymak"
- family-names: "Mahdi"
given-names: "Soltanolkotabi"
journal: "PMLR"
month: 5
title: "Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?"
year: 2019
GitHub Events
Total
- Public event: 1
Last Year
- Public event: 1