{"id":18968833,"url":"https://github.com/pylat/adaptive-bilevel-optimization","last_synced_at":"2026-01-31T06:33:28.194Z","repository":{"id":166879066,"uuid":"632927386","full_name":"pylat/adaptive-bilevel-optimization","owner":"pylat","description":"A Julia package for adaptive proximal gradient for convex bilevel optimization","archived":false,"fork":false,"pushed_at":"2023-06-15T14:06:22.000Z","size":27,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-18T02:40:06.148Z","etag":null,"topics":["adaptive-learning-rate","adaptive-proximal-algorithms","bilevel-optimization","convex-optimization","machine-learning","optimization-algorithms"],"latest_commit_sha":null,"homepage":"","language":"Julia","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/pylat.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":"2023-04-26T12:19:03.000Z","updated_at":"2024-11-28T15:20:49.000Z","dependencies_parsed_at":"2023-09-12T03:33:20.628Z","dependency_job_id":null,"html_url":"https://github.com/pylat/adaptive-bilevel-optimization","commit_stats":null,"previous_names":["pylat/adaptive-proximal-algorithms-bilevel-optimization","pylat/adaptive-bilevel-optimization"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pylat/adaptive-bilevel-optimization","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pylat%2Fadaptive-bilevel-optimization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pylat%2Fadaptive-bilevel-optimization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pylat%2Fadaptive-bilevel-optimization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pylat%2Fadaptive-bilevel-optimization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pylat","download_url":"https://codeload.github.com/pylat/adaptive-bilevel-optimization/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pylat%2Fadaptive-bilevel-optimization/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28931295,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T04:05:25.756Z","status":"ssl_error","status_checked_at":"2026-01-31T04:02:35.005Z","response_time":128,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["adaptive-learning-rate","adaptive-proximal-algorithms","bilevel-optimization","convex-optimization","machine-learning","optimization-algorithms"],"created_at":"2024-11-08T14:48:36.365Z","updated_at":"2026-01-31T06:33:28.177Z","avatar_url":"https://github.com/pylat.png","language":"Julia","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adaptive Proximal Algorithms for Convex Simple Bilevel optimization\n\nThis repository contains Julia code for the paper\n[AdaBiM: An essentially adaptive proximal gradient method for convex simple bilevel optimization](https://arxiv.org/abs/2305.03559).\n\nThe problems that can be tackled are of the form \n\n$$\n\\begin{aligned}\n    \\text{minimize} \\quad \u0026 f^1(x) + g^1(x) \\\\\n    \\text{subject to} \\quad \u0026 x \\in \\arg\\min_{w} f^2(w) + g^2(w)\n\\end{aligned}\n$$\n\nwhere $f^1,f^2$ are locally Lipschitz differentiable and $g^1,g^2$ are (possibly) nonsmooth prox-friendly functions. \n\nAlgorithms are implemented [here](./adaptive_bilevel_algorithms.jl).\n\nYou can download the datasets required in some of the experiments by running:\n\n```\njulia --project=. download_datasets.jl\n```\n\nNumerical simulations for a few different problems are contained in subfolders.\nFor example, the linear inverse problem with the $\\ell_1$ norm as the upper-level cost function can be found [here](https://github.com/pylat/adaptive-proximal-algorithms-bilevel-optimization/tree/master/experiments/logregNormL1). The `runme.jl` file includes the associated simulations. Executing `main()` will generate the plots in the same subfolder.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpylat%2Fadaptive-bilevel-optimization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpylat%2Fadaptive-bilevel-optimization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpylat%2Fadaptive-bilevel-optimization/lists"}