{"id":20247212,"url":"https://github.com/shreyansh26/ml-optimizers-jax","last_synced_at":"2025-04-10T21:32:14.050Z","repository":{"id":83435137,"uuid":"378588340","full_name":"shreyansh26/ML-Optimizers-JAX","owner":"shreyansh26","description":"Toy implementations of some popular ML optimizers using Python/JAX","archived":false,"fork":false,"pushed_at":"2021-06-20T08:08:06.000Z","size":11,"stargazers_count":44,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-24T18:52:36.717Z","etag":null,"topics":["adam","adam-optimizer","gradient-descent","jax","machine-learning","momentum","optimization-algorithms","optimizers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shreyansh26.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-06-20T07:47:57.000Z","updated_at":"2025-02-04T20:10:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"5ad42c82-a38c-4b02-a4ff-d7f5f7e2cd95","html_url":"https://github.com/shreyansh26/ML-Optimizers-JAX","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shreyansh26%2FML-Optimizers-JAX","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shreyansh26%2FML-Optimizers-JAX/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shreyansh26%2FML-Optimizers-JAX/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shreyansh26%2FML-Optimizers-JAX/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shreyansh26","download_url":"https://codeload.github.com/shreyansh26/ML-Optimizers-JAX/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248301596,"owners_count":21080924,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adam","adam-optimizer","gradient-descent","jax","machine-learning","momentum","optimization-algorithms","optimizers"],"created_at":"2024-11-14T09:36:13.080Z","updated_at":"2025-04-10T21:32:14.035Z","avatar_url":"https://github.com/shreyansh26.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## ML Optimizers from scratch using JAX\n\nImplementations of some popular optimizers from scratch for a simple model i.e., Linear Regression on a dataset of 5 features. The goal of this project was to understand how these optimizers work under the hood and try to do a toy implementation myself. I also use a bit of JAX magic to perform the differentiation of the loss function w.r.t to the weights and the bias without explicitly writing their derivatives as a separate function. This can help to generalize this notebook for other types of loss functions as well.\n\n[![Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/shreyansh2626/ml-optimizers-jax)\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/shreyansh26/ML-Optimizers-JAX/blob/master/ml_optimizers.ipynb)\n\n\nThe optimizers I have implemented are - \n* Batch Gradient Descent\n* Batch Gradient Descent + Momentum\n* Nesterov Accelerated Momentum\n* Adagrad\n* RMSprop\n* Adam\n* Adamax\n* Nadam\n* Adabelief\n\nReferences -\n* https://ruder.io/optimizing-gradient-descent/\n* https://theaisummer.com/optimization/","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshreyansh26%2Fml-optimizers-jax","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshreyansh26%2Fml-optimizers-jax","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshreyansh26%2Fml-optimizers-jax/lists"}