{"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/swalp-stochastic-weight-averaging-in-low","title":"SWALP : Stochastic Weight Averaging in Low-Precision Training","arxiv_id":"1904.11943","date":"2019-04-26","proceeding":null,"authors":["Guandao Yang","Tianyi Zhang","Polina Kirichenko","Junwen Bai","Andrew Gordon Wilson","Christopher De Sa"],"abstract":"Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages low-precision SGD iterates with a modified learning rate schedule. SWALP is easy to implement and can match the performance of full-precision SGD even with all numbers quantized down to 8 bits, including the gradient accumulators. Additionally, we show that SWALP converges arbitrarily close to the optimal solution for quadratic objectives, and to a noise ball asymptotically smaller than low precision SGD in strongly convex settings.","url_abs":"https://arxiv.org/abs/1904.11943v2","url_pdf":"https://arxiv.org/pdf/1904.11943v2.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":"swalp-stochastic-weight-averaging-in-low","repo_url":"https://github.com/stevenygd/SWALP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"swalp-stochastic-weight-averaging-in-low","repo_url":"https://github.com/RICE-EIC/Early-Bird-Tickets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"swalp-stochastic-weight-averaging-in-low","repo_url":"https://github.com/gatech-eic/early-bird-tickets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.11943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11943"}},"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/stevenygd/SWALP","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RICE-EIC/Early-Bird-Tickets","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gatech-eic/early-bird-tickets","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"583f9780bdd00a45","entry":"conv3x3","repo":"stevenygd/SWALP","repo_kind":"official","path":"models/preresnet_low.py","file_url":"https://github.com/stevenygd/SWALP/blob/HEAD/models/preresnet_low.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"4cd519a0a45fef2c","entry":"block_quantize","repo":"stevenygd/SWALP","repo_kind":"official","path":"models/quantizer.py","file_url":"https://github.com/stevenygd/SWALP/blob/HEAD/models/quantizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4cd519a0a45fef2c"}},{"code_sha256_prefix":"32f815d27919cdc0","entry":"get_data","repo":"stevenygd/SWALP","repo_kind":"official","path":"data.py","file_url":"https://github.com/stevenygd/SWALP/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"32f815d27919cdc0"}},{"code_sha256_prefix":"0895c3803b0a920b","entry":"make_layers","repo":"stevenygd/SWALP","repo_kind":"official","path":"models/vgg_low.py","file_url":"https://github.com/stevenygd/SWALP/blob/HEAD/models/vgg_low.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0895c3803b0a920b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}