{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/2105.04319","atlas_url":"https://app.syntology.ai/?focus=2105.04319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04319"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.04319"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.04319"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.04319\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2105.04319"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.04319\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.04319"},"call":"get_concepts_for_paper(arxiv_id=\"2105.04319\")"}],"by_repo":[{"repo":"TimRoith/BregmanLearning","kind":"official","samples":9,"ran":6,"instrument":0,"unverified":3}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2105.04319.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2105.04319.svg"},"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":{"ran":6,"unverified":3},"n_samples":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":9,"ran":6,"n_ran_checked":6,"n_instrument":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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-25","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"bef7c3588a8a1920","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num_classes:int/0/int, mean:float/0/float, std:float/0/float","fixture_out_type":"ResNet","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":"/code/resnet18-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bef7c3588a8a1920"}},{"code_sha256":"3a99b51deb632de7","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num_classes:int/0/int, mean:float/0/float, std:float/0/float","fixture_out_type":"ResNet","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":"/code/resnet34-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3a99b51deb632de7"}},{"code_sha256":"32785cbfb4305fcb","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num_classes:int/0/int, mean:float/0/float, std:float/0/float","fixture_out_type":"ResNet","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":"/code/resnet50-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"32785cbfb4305fcb"}},{"code_sha256":"f1b6a227e496d8f0","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"float","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f1b6a227e496d8f0"}},{"code_sha256":"8c9c1fb9fd88bac7","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"list","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8c9c1fb9fd88bac7"}},{"code_sha256":"e3035503849b4b24","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"M:list/1/callable, print_all:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e3035503849b4b24"}},{"code_sha256":"24fbacb4a8fa7e6b","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"24fbacb4a8fa7e6b"}},{"code_sha256":"77482de815b7636c","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"77482de815b7636c"}},{"code_sha256":"2f27d73dd37f8bdc","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,"code_page":"/code/get-mnist","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2f27d73dd37f8bdc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"70b8fa2098f16729d63822470e5daba1e912fcd5c5b625f39e371a591f368bfd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}