{"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/a-bregman-learning-framework-for-sparse","title":"A Bregman Learning Framework for Sparse Neural Networks","arxiv_id":"2105.04319","date":"2021-05-10","proceeding":null,"authors":["Leon Bungert","Tim Roith","Daniel Tenbrinck","Martin Burger"],"abstract":"We propose a learning framework based on stochastic Bregman iterations, also known as mirror descent, to train sparse neural networks with an inverse scale space approach. We derive a baseline algorithm called LinBreg, an accelerated version using momentum, and AdaBreg, which is a Bregmanized generalization of the Adam algorithm. In contrast to established methods for sparse training the proposed family of algorithms constitutes a regrowth strategy for neural networks that is solely optimization-based without additional heuristics. Our Bregman learning framework starts the training with very few initial parameters, successively adding only significant ones to obtain a sparse and expressive network. The proposed approach is extremely easy and efficient, yet supported by the rich mathematical theory of inverse scale space methods. We derive a statistically profound sparse parameter initialization strategy and provide a rigorous stochastic convergence analysis of the loss decay and additional convergence proofs in the convex regime. Using only 3.4% of the parameters of ResNet-18 we achieve 90.2% test accuracy on CIFAR-10, compared to 93.6% using the dense network. Our algorithm also unveils an autoencoder architecture for a denoising task. The proposed framework also has a huge potential for integrating sparse backpropagation and resource-friendly training.","url_abs":"https://arxiv.org/abs/2105.04319v3","url_pdf":"https://arxiv.org/pdf/2105.04319v3.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":"a-bregman-learning-framework-for-sparse","repo_url":"https://github.com/TimRoith/BregmanLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet","rank_in_archive_order":182,"of":265,"metrics":{"Percentage correct":"92.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.04319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04319"}},"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/TimRoith/BregmanLearning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"bef7c3588a8a1920","entry":"ResNet18","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bef7c3588a8a1920"}},{"code_sha256_prefix":"3a99b51deb632de7","entry":"ResNet34","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a99b51deb632de7"}},{"code_sha256_prefix":"32785cbfb4305fcb","entry":"ResNet50","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32785cbfb4305fcb"}},{"code_sha256_prefix":"24fbacb4a8fa7e6b","entry":"get_data_set","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"utils/datasets.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/utils/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24fbacb4a8fa7e6b"}},{"code_sha256_prefix":"77482de815b7636c","entry":"get_encoder_mnist","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"utils/datasets.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/utils/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77482de815b7636c"}},{"code_sha256_prefix":"2f27d73dd37f8bdc","entry":"get_mnist","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"utils/datasets.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/utils/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f27d73dd37f8bdc"}},{"code_sha256_prefix":"f1b6a227e496d8f0","entry":"net_sparsity","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"models/aux_funs.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/models/aux_funs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1b6a227e496d8f0"}},{"code_sha256_prefix":"8c9c1fb9fd88bac7","entry":"node_sparsity","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"models/aux_funs.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/models/aux_funs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c9c1fb9fd88bac7"}},{"code_sha256_prefix":"e3035503849b4b24","entry":"print_sparsity","repo":"TimRoith/BregmanLearning","repo_kind":"official","path":"models/aux_funs.py","file_url":"https://github.com/TimRoith/BregmanLearning/blob/HEAD/models/aux_funs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3035503849b4b24"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}