Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change bullet list to numbered list #8

Merged
merged 1 commit into from
Feb 22, 2023
Merged

Change bullet list to numbered list #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 33 additions & 28 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,16 +13,21 @@ If this repository has been useful to you in your research, please cite it using

### Table of Contents

- [Legend](#legend)
- [Survey Papers]()

- [:sparkles: Awesome Optimizers :chart\_with\_downwards\_trend:](#sparkles-awesome-optimizers-chart_with_downwards_trend)
- [Table of Contents](#table-of-contents)
- [Legend](#legend)
- [Survey Papers](#survey-papers)
- [First-order Optimizers](#first-order-optimizers)
- [Adaptive Optimizers](#adaptive-optimizers)
- [Adam family of Optimizers](#adam-family-of-optimizers)
- [Adaptive Optimizers](#adaptive-optimizers)
- [Adam Family of Optimizers](#adam-family-of-optimizers)
- [Second-order Optimizers](#second-order-optimizers)
- [Other Optimization-related Research](#other-optimisation-related-research)
- [General Improvements](#general-improvements)
- [Optimizer Analysis](#optimizer-analysis-and-meta-research)
- [Hyperparameter tuning](#hyperparameter-tuning)
- [Other Optimisation-Related Research](#other-optimisation-related-research)
- [General Improvements](#general-improvements)
- [Optimizer Analysis and Meta-research](#optimizer-analysis-and-meta-research)
- [Hyperparameter Tuning](#hyperparameter-tuning)


### Legend

| Symbol | Meaning |
Expand All @@ -31,52 +36,52 @@ If this repository has been useful to you in your research, please cite it using
| :computer: | Code |


## Survey Papers
# Survey Papers

- [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747)
1. [An overview of gradient descent optimization algorithms](https://arxiv.org/abs/1609.04747)
Sebastian Ruder; 2016

- [Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers](https://arxiv.org/abs/2007.01547)
2. [Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers](https://arxiv.org/abs/2007.01547)
Robin M. Schmidt, Frank Schneider, Philipp Hennig; 2020

## First-order Optimizers
# First-order Optimizers

- [Nesterov Accelerated Gradient momentum](https://jlmelville.github.io/mize/nesterov.html) [:outbox_tray:]() [:computer:]()
3. [Nesterov Accelerated Gradient momentum](https://jlmelville.github.io/mize/nesterov.html) [:outbox_tray:]() [:computer:]()
Yuri Nesterov; _Unknown_

- [KOALA: A Kalman Optimization Algorithm with Loss Adaptivity](https://arxiv.org/abs/2107.03331) [:outbox_tray:]() [:computer:]()
4. [KOALA: A Kalman Optimization Algorithm with Loss Adaptivity](https://arxiv.org/abs/2107.03331) [:outbox_tray:]() [:computer:]()
Aram Davtyan, Sepehr Sameni, Llukman Cerkezi, Givi Meishvilli, Adam Bielski, Paolo Favaro; 2021

### Adaptive Optimizers
## Adaptive Optimizers

- [RMSProp](http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf) [:outbox_tray:]() [:computer:]()
5. [RMSProp](http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf) [:outbox_tray:]() [:computer:]()
Geoffrey Hinton; 2013

### Adam Family of Optimizers
## Adam Family of Optimizers

- [Adam: A Method for Stochastic Optimization](https://arxiv.org/abs/1412.6980) [:outbox_tray:]() [:computer:]()
6. [Adam: A Method for Stochastic Optimization](https://arxiv.org/abs/1412.6980) [:outbox_tray:]() [:computer:]()
Diederik P. Kingma, Jimmy Ba; 2014

## Second-order Optimizers
# Second-order Optimizers

- [Shampoo: Preconditioned Stochastic Tensor Optimization](https://arxiv.org/abs/1802.09568) [:outbox_tray:]() [:computer:]()
7. [Shampoo: Preconditioned Stochastic Tensor Optimization](https://arxiv.org/abs/1802.09568) [:outbox_tray:]() [:computer:]()
Vineet Gupta, Tomer Koren, Yoram Singer


## Other Optimisation-Related Research
# Other Optimisation-Related Research

### General Improvements
- [Gradient Centralization: A New Optimization Technique for Deep Neural Networks](https://arxiv.org/abs/2004.01461) [:outbox_tray:](survey/gradient-centralization.md) [:computer:]()
## General Improvements
8. [Gradient Centralization: A New Optimization Technique for Deep Neural Networks](https://arxiv.org/abs/2004.01461) [:outbox_tray:](survey/gradient-centralization.md) [:computer:]()
Hongwei Yong, Jianqiang Huang, Xiansheng Hua, Lei Zhang; 2020


### Optimizer Analysis and Meta-research
- [On Empirical Comparisons of Optimizers for Deep Learning](https://arxiv.org/abs/1910.05446) [:outbox_tray:]()
## Optimizer Analysis and Meta-research
9. [On Empirical Comparisons of Optimizers for Deep Learning](https://arxiv.org/abs/1910.05446) [:outbox_tray:]()
Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee, Chris J. Maddison, George E. Dahl; 2019

- [Adam Can Converge Without Any Modification on Update Rules](https://arxiv.org/abs/2208.09632) [:outbox_tray:](survey/adam-can-converge.md)
10. [Adam Can Converge Without Any Modification on Update Rules](https://arxiv.org/abs/2208.09632) [:outbox_tray:](survey/adam-can-converge.md)
Yushun Zhang, Congliang Chen, Naichen Shi, Ruoyu Sun, Zhi-Quan Luo; 2022

### Hyperparameter Tuning
- [Gradient Descent: The Ultimate Optimizer](https://arxiv.org/abs/1909.13371) [:outbox_tray:]() [:computer:]()
## Hyperparameter Tuning
11. [Gradient Descent: The Ultimate Optimizer](https://arxiv.org/abs/1909.13371) [:outbox_tray:]() [:computer:]()
Kartik Chandra, Audrey Xie, Jonathan Ragan-Kelley, Erik Meijer; 2019