{"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/permute-to-train-a-new-dimension-to-training","title":"Train-by-Reconnect: Decoupling Locations of Weights from their Values","arxiv_id":"2003.02570","date":"2020-03-05","proceeding":"NeurIPS 2020 12","authors":["Yushi Qiu","Reiji Suda"],"abstract":"What makes untrained deep neural networks (DNNs) different from the trained performant ones? By zooming into the weights in well-trained DNNs, we found it is the location of weights that hold most of the information encoded by the training. Motivated by this observation, we hypothesize that weights in stochastic gradient-based method trained DNNs can be separated into two dimensions: the locations of weights and their exact values. To assess our hypothesis, we propose a novel method named Lookahead Permutation (LaPerm) to train DNNs by reconnecting the weights. We empirically demonstrate the versatility of LaPerm while producing extensive evidence to support our hypothesis: when the initial weights are random and dense, our method demonstrates speed and performance similar to or better than that of regular optimizers, e.g., Adam; when the initial weights are random and sparse (many zeros), our method changes the way neurons connect and reach accuracy comparable to that of a well-trained fully initialized network; when the initial weights share a single value, our method finds weight agnostic neural network with far better-than-chance accuracy.","url_abs":"https://arxiv.org/abs/2003.02570v6","url_pdf":"https://arxiv.org/pdf/2003.02570v6.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":"permute-to-train-a-new-dimension-to-training","repo_url":"https://github.com/ihsuy/Train-by-Reconnect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"lookahead","method_name":"Lookahead"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.02570","atlas_url":"https://app.syntology.ai/?focus=2003.02570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02570"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ihsuy/Train-by-Reconnect","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":"2236035030277f4d","entry":"LaPerm","repo":"ihsuy/Train-by-Reconnect","repo_kind":"listed","path":"train_by_reconnect/LaPerm.py","file_url":"https://github.com/ihsuy/Train-by-Reconnect/blob/HEAD/train_by_reconnect/LaPerm.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":"2236035030277f4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}