{"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-modular-approach-to-block-diagonal-hessian","title":"Modular Block-diagonal Curvature Approximations for Feedforward Architectures","arxiv_id":"1902.01813","date":"2019-02-05","proceeding":null,"authors":["Felix Dangel","Stefan Harmeling","Philipp Hennig"],"abstract":"We propose a modular extension of backpropagation for the computation of block-diagonal approximations to various curvature matrices of the training objective (in particular, the Hessian, generalized Gauss-Newton, and positive-curvature Hessian). The approach reduces the otherwise tedious manual derivation of these matrices into local modules, and is easy to integrate into existing machine learning libraries. Moreover, we develop a compact notation derived from matrix differential calculus. We outline different strategies applicable to our method. They subsume recently-proposed block-diagonal approximations as special cases, and are extended to convolutional neural networks in this work.","url_abs":"https://arxiv.org/abs/1902.01813v3","url_pdf":"https://arxiv.org/pdf/1902.01813v3.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-modular-approach-to-block-diagonal-hessian","repo_url":"https://github.com/f-dangel/hbp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.01813","atlas_url":"https://app.syntology.ai/?focus=1902.01813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01813"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/f-dangel/hbp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"7a9d3012348d3892","entry":"batch_summed_hessian","repo":"f-dangel/hbp","repo_kind":"official","path":"bpexts/hbp/loss.py","file_url":"https://github.com/f-dangel/hbp/blob/HEAD/bpexts/hbp/loss.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":"7a9d3012348d3892"}},{"code_sha256_prefix":"1cace52fec18df3f","entry":"hbp_decorate","repo":"f-dangel/hbp","repo_kind":"official","path":"bpexts/hbp/module.py","file_url":"https://github.com/f-dangel/hbp/blob/HEAD/bpexts/hbp/module.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":"1cace52fec18df3f"}},{"code_sha256_prefix":"0043d66c29c327c1","entry":"hbp_elementwise_nonlinear","repo":"f-dangel/hbp","repo_kind":"official","path":"bpexts/hbp/nonlinear.py","file_url":"https://github.com/f-dangel/hbp/blob/HEAD/bpexts/hbp/nonlinear.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":"0043d66c29c327c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}