{"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/comq-a-backpropagation-free-algorithm-for","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","arxiv_id":"2403.07134","date":"2024-03-11","proceeding":null,"authors":["Aozhong zhang","Zi Yang","Naigang Wang","Yingyong Qi","Jack Xin","Xin Li","Penghang Yin"],"abstract":"Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterparts without compromising the original accuracy remains a key challenge. In this paper, we propose an innovative PTQ algorithm termed COMQ, which sequentially conducts coordinate-wise minimization of the layer-wise reconstruction errors. We consider the widely used integer quantization, where every quantized weight can be decomposed into a shared floating-point scalar and an integer bit-code. Within a fixed layer, COMQ treats all the scaling factor(s) and bit-codes as the variables of the reconstruction error. Every iteration improves this error along a single coordinate while keeping all other variables constant. COMQ is easy to use and requires no hyper-parameter tuning. It instead involves only dot products and rounding operations. We update these variables in a carefully designed greedy order, significantly enhancing the accuracy. COMQ achieves remarkable results in quantizing 4-bit Vision Transformers, with a negligible loss of less than 1% in Top-1 accuracy. In 4-bit INT quantization of convolutional neural networks, COMQ maintains near-lossless accuracy with a minimal drop of merely 0.3% in Top-1 accuracy.","url_abs":"https://arxiv.org/abs/2403.07134v3","url_pdf":"https://arxiv.org/pdf/2403.07134v3.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":"comq-a-backpropagation-free-algorithm-for","repo_url":"https://github.com/aozhongzhang/comq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.07134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07134"}},"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/aozhongzhang/comq","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"988183aec473225d","entry":"Layer_input","repo":"aozhongzhang/comq","repo_kind":"official","path":"modelutils.py","file_url":"https://github.com/aozhongzhang/comq/blob/HEAD/modelutils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"988183aec473225d"}},{"code_sha256_prefix":"c330d1f7ea1cc699","entry":"data_loader","repo":"aozhongzhang/comq","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/aozhongzhang/comq/blob/HEAD/datautils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c330d1f7ea1cc699"}},{"code_sha256_prefix":"4ba167d9b5a33c6d","entry":"parse_imagenet_val_labels","repo":"aozhongzhang/comq","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/aozhongzhang/comq/blob/HEAD/datautils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ba167d9b5a33c6d"}},{"code_sha256_prefix":"c416ed2477b56285","entry":"test_accuracy","repo":"aozhongzhang/comq","repo_kind":"official","path":"quantize_main.py","file_url":"https://github.com/aozhongzhang/comq/blob/HEAD/quantize_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c416ed2477b56285"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}