{"id":30524036,"url":"https://github.com/lightonai/double-descent-curve","last_synced_at":"2025-08-26T20:52:32.659Z","repository":{"id":40972599,"uuid":"233594770","full_name":"lightonai/double-descent-curve","owner":"lightonai","description":"Double Descent Curve with Optical Random Features","archived":false,"fork":false,"pushed_at":"2022-06-22T00:08:15.000Z","size":150,"stargazers_count":23,"open_issues_count":1,"forks_count":5,"subscribers_count":6,"default_branch":"master","last_synced_at":"2023-03-04T05:22:23.492Z","etag":null,"topics":["machine-learning","optical-network","photonic-computing","random-features","ridge-regression"],"latest_commit_sha":null,"homepage":"https://medium.com/@LightOnIO/beyond-overfitting-and-beyond-silicon-the-double-descent-curve-18b6d9810e1b","language":"Jupyter Notebook","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/lightonai.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}},"created_at":"2020-01-13T12:51:58.000Z","updated_at":"2023-02-01T07:15:00.000Z","dependencies_parsed_at":"2022-09-17T03:51:43.045Z","dependency_job_id":null,"html_url":"https://github.com/lightonai/double-descent-curve","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"purl":"pkg:github/lightonai/double-descent-curve","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightonai%2Fdouble-descent-curve","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightonai%2Fdouble-descent-curve/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightonai%2Fdouble-descent-curve/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightonai%2Fdouble-descent-curve/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lightonai","download_url":"https://codeload.github.com/lightonai/double-descent-curve/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightonai%2Fdouble-descent-curve/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272254567,"owners_count":24901068,"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","status":"online","status_checked_at":"2025-08-26T02:00:07.904Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["machine-learning","optical-network","photonic-computing","random-features","ridge-regression"],"created_at":"2025-08-26T20:52:31.850Z","updated_at":"2025-08-26T20:52:32.644Z","avatar_url":"https://github.com/lightonai.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Double Descent Curve\nThis is the code to reproduce Figure 5 and 6 of [\"The double descent risk curve\"](https://medium.com/@LightOnIO/beyond-overfitting-and-beyond-silicon-the-double-descent-curve-18b6d9810e1b) blog post on Medium.\n\nThis script recovers the double descent curve using random projections plus the `RidgeClassifier` from `scikit-learn`. \nIt is possible to choose between a synthetic optical processing unit (OPU) and the real OPU. \nTo request access to our cloud and try our optics-based hardware, contact us: https://www.lighton.ai/contact-us/\n\n## Access to Optical Processing Units\n\nTo request access to LightOn Cloud and try our photonic co-processor, please visit: https://cloud.lighton.ai/\n\nFor researchers, we also have a LightOn Cloud for Research program, please visit https://cloud.lighton.ai/lighton-research/ for more information.\n\n## Run the experiments\n```\npython ddc_ridgeclassifier.py  # to use synthetic opu on mnist\npython ddc_ridgeclassifier.py  -dataset 'cifar10' # to use synthetic opu on cifar10 \npython ddc_ridgeclassifier.py -is_real_opu True  # to use opu on mnist with  threshold encoder \npython ddc_ridgeclassifier.py -is_real_opu True  -encoding_method 'autoencoder' # to use opu on mnist with autoencoder \npython ddc_ridgeclassifier.py -is_real_opu True -dataset 'cifar10' # to use opu on cifar10 with  threshold encoder \npython ddc_ridgeclassifier.py -is_real_opu True  -encoding_method 'autoencoder'  -dataset 'cifaro10'# to use opu on cifar10 with autoencoder \n```\n\nRunning `ddc_ridgeclassifier.py` outputs a `.pkl` file. To plot the results using this file look at the `plot.ipynb` example.  \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightonai%2Fdouble-descent-curve","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flightonai%2Fdouble-descent-curve","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightonai%2Fdouble-descent-curve/lists"}