{"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/bsq-exploring-bit-level-sparsity-for-mixed-1","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","arxiv_id":"2102.10462","date":"2021-02-20","proceeding":"ICLR 2021 1","authors":["Huanrui Yang","Lin Duan","Yiran Chen","Hai Li"],"abstract":"Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the exact quantization scheme. Previous methods either examine only a small manually-designed search space or utilize a cumbersome neural architecture search to explore the vast search space. These approaches cannot lead to an optimal quantization scheme efficiently. This work proposes bit-level sparsity quantization (BSQ) to tackle the mixed-precision quantization from a new angle of inducing bit-level sparsity. We consider each bit of quantized weights as an independent trainable variable and introduce a differentiable bit-sparsity regularizer. BSQ can induce all-zero bits across a group of weight elements and realize the dynamic precision reduction, leading to a mixed-precision quantization scheme of the original model. Our method enables the exploration of the full mixed-precision space with a single gradient-based optimization process, with only one hyperparameter to tradeoff the performance and compression. BSQ achieves both higher accuracy and higher bit reduction on various model architectures on the CIFAR-10 and ImageNet datasets comparing to previous methods.","url_abs":"https://arxiv.org/abs/2102.10462v1","url_pdf":"https://arxiv.org/pdf/2102.10462v1.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":"bsq-exploring-bit-level-sparsity-for-mixed-1","repo_url":"https://github.com/yanghr/BSQ","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2102.10462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.10462"}},"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/yanghr/BSQ","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"a770cec318d7e9cf","entry":"BitLinear","repo":"yanghr/BSQ","repo_kind":"official","path":"models/cifar/bit.py","file_url":"https://github.com/yanghr/BSQ/blob/HEAD/models/cifar/bit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a770cec318d7e9cf"}},{"code_sha256_prefix":"3da1b11a0ac941dc","entry":"bit_STE","repo":"yanghr/BSQ","repo_kind":"official","path":"models/cifar/bit.py","file_url":"https://github.com/yanghr/BSQ/blob/HEAD/models/cifar/bit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3da1b11a0ac941dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}