{"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/loss-aware-post-training-quantization","title":"Loss Aware Post-training Quantization","arxiv_id":"1911.07190","date":"2019-11-17","proceeding":null,"authors":["Yury Nahshan","Brian Chmiel","Chaim Baskin","Evgenii Zheltonozhskii","Ron Banner","Alex M. Bronstein","Avi Mendelson"],"abstract":"Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for INT4 (or lower) but provide reasonable accuracy for INT8 (or above). In this work, we study the effect of quantization on the structure of the loss landscape. Additionally, we show that the structure is flat and separable for mild quantization, enabling straightforward post-training quantization methods to achieve good results. We show that with more aggressive quantization, the loss landscape becomes highly non-separable with steep curvature, making the selection of quantization parameters more challenging. Armed with this understanding, we design a method that quantizes the layer parameters jointly, enabling significant accuracy improvement over current post-training quantization methods. Reference implementation is available at https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq","url_abs":"https://arxiv.org/abs/1911.07190v2","url_pdf":"https://arxiv.org/pdf/1911.07190v2.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":"loss-aware-post-training-quantization","repo_url":"https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"loss-aware-post-training-quantization","repo_url":"https://github.com/ynahshan/nn-quantization-pytorch","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.07190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.07190"}},"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/ynahshan/nn-quantization-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1},"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":2,"samples":[{"code_sha256_prefix":"8de964d73bb95d24","entry":"coord_descent","repo":"ynahshan/nn-quantization-pytorch","repo_kind":"official","path":"lapq/lapq_linear_parametrization.py","file_url":"https://github.com/ynahshan/nn-quantization-pytorch/blob/HEAD/lapq/lapq_linear_parametrization.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8de964d73bb95d24"}},{"code_sha256_prefix":"11be95863e61b64d","entry":"evaluate_calibration_clipped","repo":"ynahshan/nn-quantization-pytorch","repo_kind":"official","path":"lapq/lapq_linear_parametrization.py","file_url":"https://github.com/ynahshan/nn-quantization-pytorch/blob/HEAD/lapq/lapq_linear_parametrization.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"11be95863e61b64d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}