{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-weakly-convex-regularizers-for","title":"Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms","arxiv_id":"2308.10542","date":"2023-08-21","proceeding":null,"authors":["Alexis Goujon","Sebastian Neumayer","Michael Unser"],"abstract":"We propose to learn non-convex regularizers with a prescribed upper bound on their weak-convexity modulus. Such regularizers give rise to variational denoisers that minimize a convex energy. They rely on few parameters (less than 15,000) and offer a signal-processing interpretation as they mimic handcrafted sparsity-promoting regularizers. Through numerical experiments, we show that such denoisers outperform convex-regularization methods as well as the popular BM3D denoiser. Additionally, the learned regularizer can be deployed to solve inverse problems with iterative schemes that provably converge. For both CT and MRI reconstruction, the regularizer generalizes well and offers an excellent tradeoff between performance, number of parameters, guarantees, and interpretability when compared to other data-driven approaches.","url_abs":"https://arxiv.org/abs/2308.10542v2","url_pdf":"https://arxiv.org/pdf/2308.10542v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-weakly-convex-regularizers-for","repo_url":"https://github.com/axgoujon/convex_ridge_regularizers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-weakly-convex-regularizers-for","repo_url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"mri-reconstruction","task_name":"MRI Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.10542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10542"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/axgoujon/convex_ridge_regularizers","reach":{"status":"ok"}}],"summary":{"ran":9,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":11,"samples":[{"code_sha256_prefix":"8ac5d841e6a79245","entry":"accelerated_gd","repo":"axgoujon/convex_ridge_regularizers","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/axgoujon/convex_ridge_regularizers/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ac5d841e6a79245"}},{"code_sha256_prefix":"cb0bb50231eaf2ae","entry":"accelerated_gd_batch","repo":"axgoujon/weakly_convex_ridge_regularizer","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb0bb50231eaf2ae"}},{"code_sha256_prefix":"f68fef30f6b7a343","entry":"anderson","repo":"axgoujon/weakly_convex_ridge_regularizer","repo_kind":"official","path":"models/deep_equilibrium.py","file_url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer/blob/HEAD/models/deep_equilibrium.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f68fef30f6b7a343"}},{"code_sha256_prefix":"1391a8ffffc258ce","entry":"batch_PSNR","repo":"axgoujon/weakly_convex_ridge_regularizer","repo_kind":"official","path":"training/utils/utilities.py","file_url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer/blob/HEAD/training/utils/utilities.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1391a8ffffc258ce"}},{"code_sha256_prefix":"352b38f06c956d4d","entry":"initialize_coeffs","repo":"axgoujon/convex_ridge_regularizers","repo_kind":"official","path":"models/linear_spline.py","file_url":"https://github.com/axgoujon/convex_ridge_regularizers/blob/HEAD/models/linear_spline.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"352b38f06c956d4d"}},{"code_sha256_prefix":"fab44524ecb8e8e7","entry":"monotonic_clipping","repo":"axgoujon/convex_ridge_regularizers","repo_kind":"official","path":"models/linear_spline.py","file_url":"https://github.com/axgoujon/convex_ridge_regularizers/blob/HEAD/models/linear_spline.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fab44524ecb8e8e7"}},{"code_sha256_prefix":"46884280e3f87a22","entry":"norm","repo":"axgoujon/convex_ridge_regularizers","repo_kind":"official","path":"models/convex_ridge_regularizer.py","file_url":"https://github.com/axgoujon/convex_ridge_regularizers/blob/HEAD/models/convex_ridge_regularizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"46884280e3f87a22"}},{"code_sha256_prefix":"4bd5705e5d9f6cf3","entry":"normalize","repo":"axgoujon/convex_ridge_regularizers","repo_kind":"official","path":"models/convex_ridge_regularizer.py","file_url":"https://github.com/axgoujon/convex_ridge_regularizers/blob/HEAD/models/convex_ridge_regularizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4bd5705e5d9f6cf3"}},{"code_sha256_prefix":"a87c23b077bc5422","entry":"normalize","repo":"axgoujon/convex_ridge_regularizers","repo_kind":"official","path":"models/multi_conv.py","file_url":"https://github.com/axgoujon/convex_ridge_regularizers/blob/HEAD/models/multi_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a87c23b077bc5422"}},{"code_sha256_prefix":"6cb81e2b8904dc02","entry":"accelerated_gd_single","repo":"axgoujon/weakly_convex_ridge_regularizer","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6cb81e2b8904dc02"}},{"code_sha256_prefix":"67ff6220b6301f8f","entry":"batch_SSIM","repo":"axgoujon/weakly_convex_ridge_regularizer","repo_kind":"official","path":"training/utils/utilities.py","file_url":"https://github.com/axgoujon/weakly_convex_ridge_regularizer/blob/HEAD/training/utils/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"67ff6220b6301f8f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}