{"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/re-parameterizing-your-optimizers-rather-than","title":"Re-parameterizing Your Optimizers rather than Architectures","arxiv_id":"2205.15242","date":"2022-05-30","proceeding":null,"authors":["Xiaohan Ding","Honghao Chen","Xiangyu Zhang","Kaiqi Huang","Jungong Han","Guiguang Ding"],"abstract":"The well-designed structures in neural networks reflect the prior knowledge incorporated into the models. However, though different models have various priors, we are used to training them with model-agnostic optimizers such as SGD. In this paper, we propose to incorporate model-specific prior knowledge into optimizers by modifying the gradients according to a set of model-specific hyper-parameters. Such a methodology is referred to as Gradient Re-parameterization, and the optimizers are named RepOptimizers. For the extreme simplicity of model structure, we focus on a VGG-style plain model and showcase that such a simple model trained with a RepOptimizer, which is referred to as RepOpt-VGG, performs on par with or better than the recent well-designed models. From a practical perspective, RepOpt-VGG is a favorable base model because of its simple structure, high inference speed and training efficiency. Compared to Structural Re-parameterization, which adds priors into models via constructing extra training-time structures, RepOptimizers require no extra forward/backward computations and solve the problem of quantization. We hope to spark further research beyond the realms of model structure design. Code and models \\url{https://github.com/DingXiaoH/RepOptimizers}.","url_abs":"https://arxiv.org/abs/2205.15242v4","url_pdf":"https://arxiv.org/pdf/2205.15242v4.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":"re-parameterizing-your-optimizers-rather-than","repo_url":"https://github.com/dingxiaoh/repoptimizers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.15242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15242"}},"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":"deterministic:regex_extraction","url":"https://github.com/DingXiaoH/RepOptimizers","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dingxiaoh/repoptimizers","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":"21ba78e703ceb61b","entry":"LinearAddBlock","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21ba78e703ceb61b"}},{"code_sha256_prefix":"f369e3b0848c69e6","entry":"RealVGGBlock","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f369e3b0848c69e6"}},{"code_sha256_prefix":"d6f27f1009cbeacb","entry":"SEBlock","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6f27f1009cbeacb"}},{"code_sha256_prefix":"3599b9e1a7349fea","entry":"ScaleLayer","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3599b9e1a7349fea"}},{"code_sha256_prefix":"2d679e0ac76635db","entry":"get_equivalent_kernel","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"check_equivalency.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/check_equivalency.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d679e0ac76635db"}},{"code_sha256_prefix":"b4a924296154005e","entry":"RepOptVGGHandler","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4a924296154005e"}},{"code_sha256_prefix":"d8b8bfd2c9da41cf","entry":"RepOptimizerHandler","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8b8bfd2c9da41cf"}},{"code_sha256_prefix":"73204d5c8e3a1d64","entry":"extract_blocks_into_list","repo":"dingxiaoh/repoptimizers","repo_kind":"official","path":"repoptimizer/repoptvgg_impl.py","file_url":"https://github.com/dingxiaoh/repoptimizers/blob/HEAD/repoptimizer/repoptvgg_impl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73204d5c8e3a1d64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}