{"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/one-ticket-to-win-them-all-generalizing","title":"One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers","arxiv_id":"1906.02773","date":"2019-06-06","proceeding":"NeurIPS 2019 12","authors":["Ari S. Morcos","Haonan Yu","Michela Paganini","Yuandong Tian"],"abstract":"The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately. Unfortunately, finding these \"winning ticket\" initializations is computationally expensive. One potential solution is to reuse the same winning tickets across a variety of datasets and optimizers. However, the generality of winning ticket initializations remains unclear. Here, we attempt to answer this question by generating winning tickets for one training configuration (optimizer and dataset) and evaluating their performance on another configuration. Perhaps surprisingly, we found that, within the natural images domain, winning ticket initializations generalized across a variety of datasets, including Fashion MNIST, SVHN, CIFAR-10/100, ImageNet, and Places365, often achieving performance close to that of winning tickets generated on the same dataset. Moreover, winning tickets generated using larger datasets consistently transferred better than those generated using smaller datasets. We also found that winning ticket initializations generalize across optimizers with high performance. These results suggest that winning ticket initializations generated by sufficiently large datasets contain inductive biases generic to neural networks more broadly which improve training across many settings and provide hope for the development of better initialization methods.","url_abs":"https://arxiv.org/abs/1906.02773v2","url_pdf":"https://arxiv.org/pdf/1906.02773v2.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":"one-ticket-to-win-them-all-generalizing","repo_url":"https://github.com/ismail31416/colt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"one-ticket-to-win-them-all-generalizing","repo_url":"https://github.com/varungohil/Generalizing-Lottery-Tickets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02773"}},"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/varungohil/Generalizing-Lottery-Tickets","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ismail31416/colt","reach":null}],"summary":{"ran_violates":1,"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"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":"c48f350f6d321cd0","entry":"get_20_percent","repo":"varungohil/Generalizing-Lottery-Tickets","repo_kind":"listed","path":"src/iterative_pruning.py","file_url":"https://github.com/varungohil/Generalizing-Lottery-Tickets/blob/HEAD/src/iterative_pruning.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c48f350f6d321cd0"}},{"code_sha256_prefix":"4efe71ec2340b424","entry":"modelselect","repo":"ismail31416/colt","repo_kind":"listed","path":"main-full.py","file_url":"https://github.com/ismail31416/colt/blob/HEAD/main-full.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4efe71ec2340b424"}},{"code_sha256_prefix":"895e488cbc2f1d73","entry":"modelselect","repo":"ismail31416/colt","repo_kind":"listed","path":"transfer.py","file_url":"https://github.com/ismail31416/colt/blob/HEAD/transfer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"895e488cbc2f1d73"}},{"code_sha256_prefix":"e33fdf660fdbaec4","entry":"permute_masks","repo":"varungohil/Generalizing-Lottery-Tickets","repo_kind":"listed","path":"src/iterative_pruning.py","file_url":"https://github.com/varungohil/Generalizing-Lottery-Tickets/blob/HEAD/src/iterative_pruning.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e33fdf660fdbaec4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}