{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/switch-ema-a-free-lunch-for-better-flatness","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","arxiv_id":"2402.09240","date":"2024-02-14","proceeding":null,"authors":["Siyuan Li","Zicheng Liu","Juanxi Tian","Ge Wang","Zedong Wang","Weiyang Jin","Di wu","Cheng Tan","Tao Lin","Yang Liu","Baigui Sun","Stan Z. Li"],"abstract":"Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization. Despite achieving better flatness, existing WA methods might fall into worse final performances or require extra test-time computations. This work unveils the full potential of EMA with a single line of modification, i.e., switching the EMA parameters to the original model after each epoch, dubbed as Switch EMA (SEMA). From both theoretical and empirical aspects, we demonstrate that SEMA can help DNNs to reach generalization optima that better trade-off between flatness and sharpness. To verify the effectiveness of SEMA, we conduct comparison experiments with discriminative, generative, and regression tasks on vision and language datasets, including image classification, self-supervised learning, object detection and segmentation, image generation, video prediction, attribute regression, and language modeling. Comprehensive results with popular optimizers and networks show that SEMA is a free lunch for DNN training by improving performances and boosting convergence speeds.","url_abs":"https://arxiv.org/abs/2402.09240v2","url_pdf":"https://arxiv.org/pdf/2402.09240v2.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":"switch-ema-a-free-lunch-for-better-flatness","repo_url":"https://github.com/westlake-ai/sema","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"switch-ema-a-free-lunch-for-better-flatness","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"switch-ema-a-free-lunch-for-better-flatness","repo_url":"https://github.com/lucidrains/ema-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"video-prediction","task_name":"Video Prediction"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.09240","atlas_url":"https://app.syntology.ai/?focus=2402.09240","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2402.09240"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.09240\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.09240"},"call":"get_concepts_for_paper(arxiv_id=\"2402.09240\")"}],"by_repo":[{"repo":"westlake-ai/sema","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Westlake-AI/openmixup","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1710.09412","1712.09913","1905.04899","2312.11954"],"harvested_for_calls":[{"arxiv_id":"1710.09412","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.09412"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.09412\")"},{"arxiv_id":"1712.09913","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1712.09913"},"call":"get_harvested_code_for_paper(arxiv_id=\"1712.09913\")"},{"arxiv_id":"1905.04899","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1905.04899"},"call":"get_harvested_code_for_paper(arxiv_id=\"1905.04899\")"},{"arxiv_id":"2312.11954","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.11954"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.11954\")"}]},{"repo":"lucidrains/ema-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.02696"],"harvested_for_calls":[{"arxiv_id":"2312.02696","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.02696"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.02696\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3455c841c7b3a87c873375b5dcb0451d086936139c38dc6af9cbdc4c60dd3832","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}