{"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/latent-weights-do-not-exist-rethinking","title":"Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization","arxiv_id":"1906.02107","date":"2019-06-05","proceeding":"NeurIPS 2019 12","authors":["Koen Helwegen","James Widdicombe","Lukas Geiger","Zechun Liu","Kwang-Ting Cheng","Roeland Nusselder"],"abstract":"Optimization of Binarized Neural Networks (BNNs) currently relies on real-valued latent weights to accumulate small update steps. In this paper, we argue that these latent weights cannot be treated analogously to weights in real-valued networks. Instead their main role is to provide inertia during training. We interpret current methods in terms of inertia and provide novel insights into the optimization of BNNs. We subsequently introduce the first optimizer specifically designed for BNNs, Binary Optimizer (Bop), and demonstrate its performance on CIFAR-10 and ImageNet. Together, the redefinition of latent weights as inertia and the introduction of Bop enable a better understanding of BNN optimization and open up the way for further improvements in training methodologies for BNNs. Code is available at: https://github.com/plumerai/rethinking-bnn-optimization","url_abs":"https://arxiv.org/abs/1906.02107v2","url_pdf":"https://arxiv.org/pdf/1906.02107v2.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":"latent-weights-do-not-exist-rethinking","repo_url":"https://github.com/plumerai/rethinking-bnn-optimization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"latent-weights-do-not-exist-rethinking","repo_url":"https://github.com/nikvaessen/Rethinking-Binarized-Neural-Network-Optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"latent-weights-do-not-exist-rethinking","repo_url":"https://github.com/larq/larq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.02107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02107"}},"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/nikvaessen/Rethinking-Binarized-Neural-Network-Optimization","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/plumerai/rethinking-bnn-optimization","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/larq/larq","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":7,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"acb8b424bd1c956c","entry":"are_layers_equal","repo":"nikvaessen/Rethinking-Binarized-Neural-Network-Optimization","repo_kind":"listed","path":"research_seed/theoretical/larq_approximation_viewpoint_cifar.py","file_url":"https://github.com/nikvaessen/Rethinking-Binarized-Neural-Network-Optimization/blob/HEAD/research_seed/theoretical/larq_approximation_viewpoint_cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"acb8b424bd1c956c"}},{"code_sha256_prefix":"0db3e7ce00a6d3fa","entry":"get_current_epoch","repo":"plumerai/rethinking-bnn-optimization","repo_kind":"official","path":"bnn_optimization/utils.py","file_url":"https://github.com/plumerai/rethinking-bnn-optimization/blob/HEAD/bnn_optimization/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0db3e7ce00a6d3fa"}},{"code_sha256_prefix":"d62edadba5083a4d","entry":"get_distribution_scope","repo":"plumerai/rethinking-bnn-optimization","repo_kind":"official","path":"bnn_optimization/utils.py","file_url":"https://github.com/plumerai/rethinking-bnn-optimization/blob/HEAD/bnn_optimization/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d62edadba5083a4d"}},{"code_sha256_prefix":"b877c5a8c2435a58","entry":"heaviside","repo":"larq/larq","repo_kind":"listed","path":"larq/math.py","file_url":"https://github.com/larq/larq/blob/HEAD/larq/math.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b877c5a8c2435a58"}},{"code_sha256_prefix":"753267d7a888690b","entry":"sanitize_table","repo":"larq/larq","repo_kind":"listed","path":"larq/models.py","file_url":"https://github.com/larq/larq/blob/HEAD/larq/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"753267d7a888690b"}},{"code_sha256_prefix":"a7204bb0e23dc1a2","entry":"sign","repo":"larq/larq","repo_kind":"listed","path":"larq/math.py","file_url":"https://github.com/larq/larq/blob/HEAD/larq/math.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7204bb0e23dc1a2"}},{"code_sha256_prefix":"fe3050fba6a31ee2","entry":"test_model","repo":"nikvaessen/Rethinking-Binarized-Neural-Network-Optimization","repo_kind":"listed","path":"research_seed/theoretical/larq_approximation_viewpoint_cifar.py","file_url":"https://github.com/nikvaessen/Rethinking-Binarized-Neural-Network-Optimization/blob/HEAD/research_seed/theoretical/larq_approximation_viewpoint_cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe3050fba6a31ee2"}},{"code_sha256_prefix":"576d4e99e5399660","entry":"test_model","repo":"nikvaessen/Rethinking-Binarized-Neural-Network-Optimization","repo_kind":"listed","path":"research_seed/theoretical/larq_approximation_viewpoint_mnist.py","file_url":"https://github.com/nikvaessen/Rethinking-Binarized-Neural-Network-Optimization/blob/HEAD/research_seed/theoretical/larq_approximation_viewpoint_mnist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"576d4e99e5399660"}},{"code_sha256_prefix":"8a2e32e7dd71db12","entry":"test_model","repo":"nikvaessen/Rethinking-Binarized-Neural-Network-Optimization","repo_kind":"listed","path":"research_seed/theoretical/larq_theorem_cifar.py","file_url":"https://github.com/nikvaessen/Rethinking-Binarized-Neural-Network-Optimization/blob/HEAD/research_seed/theoretical/larq_theorem_cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a2e32e7dd71db12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}