{"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/sanity-checking-pruning-methods-random","title":"Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot","arxiv_id":"2009.11094","date":"2020-09-22","proceeding":"NeurIPS 2020 12","authors":["Jingtong Su","Yihang Chen","Tianle Cai","Tianhao Wu","Ruiqi Gao","Li-Wei Wang","Jason D. Lee"],"abstract":"Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation. Conventional wisdom of pruning algorithms suggests that: (1) Pruning methods exploit information from training data to find good subnetworks; (2) The architecture of the pruned network is crucial for good performance. In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call \"initial tickets\"), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance. These findings inspire us to choose a series of simple \\emph{data-independent} prune ratios for each layer, and randomly prune each layer accordingly to get a subnetwork (which we call \"random tickets\"). Experimental results show that our zero-shot random tickets outperform or attain a similar performance compared to existing \"initial tickets\". In addition, we identify one existing pruning method that passes our sanity checks. We hybridize the ratios in our random ticket with this method and propose a new method called \"hybrid tickets\", which achieves further improvement. (Our code is publicly available at https://github.com/JingtongSu/sanity-checking-pruning)","url_abs":"https://arxiv.org/abs/2009.11094v2","url_pdf":"https://arxiv.org/pdf/2009.11094v2.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":"sanity-checking-pruning-methods-random","repo_url":"https://github.com/JingtongSu/sanity-checking-pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.11094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11094"}},"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/JingtongSu/sanity-checking-pruning","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/alecwangcq/GraSP","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Eric-mingjie/rethinking-network-pruning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":2,"unverified":4},"by_repo_kind":{"found_in_text":{"samples":7,"ran":3,"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":"029647da91b3ee45","entry":"GraSP_fetch_data","repo":"alecwangcq/GraSP","repo_kind":"found_in_text","path":"pruner/GraSP.py","file_url":"https://github.com/alecwangcq/GraSP/blob/HEAD/pruner/GraSP.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":"029647da91b3ee45"}},{"code_sha256_prefix":"dd41a92a0afa4fd7","entry":"count_fc_parameters","repo":"alecwangcq/GraSP","repo_kind":"found_in_text","path":"pruner/GraSP.py","file_url":"https://github.com/alecwangcq/GraSP/blob/HEAD/pruner/GraSP.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd41a92a0afa4fd7"}},{"code_sha256_prefix":"155c0c245324ce36","entry":"count_total_parameters","repo":"alecwangcq/GraSP","repo_kind":"found_in_text","path":"pruner/GraSP.py","file_url":"https://github.com/alecwangcq/GraSP/blob/HEAD/pruner/GraSP.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"155c0c245324ce36"}},{"code_sha256_prefix":"bc77b97e85fefaa4","entry":"GraSP","repo":"alecwangcq/GraSP","repo_kind":"found_in_text","path":"pruner/GraSP.py","file_url":"https://github.com/alecwangcq/GraSP/blob/HEAD/pruner/GraSP.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":"bc77b97e85fefaa4"}},{"code_sha256_prefix":"6f215c4ac07fc796","entry":"count_model_param_flops","repo":"Eric-mingjie/rethinking-network-pruning","repo_kind":"found_in_text","path":"imagenet/l1-norm-pruning/compute_flops.py","file_url":"https://github.com/Eric-mingjie/rethinking-network-pruning/blob/HEAD/imagenet/l1-norm-pruning/compute_flops.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":"6f215c4ac07fc796"}},{"code_sha256_prefix":"dbcc7f02b0356238","entry":"print_model_param_flops","repo":"Eric-mingjie/rethinking-network-pruning","repo_kind":"found_in_text","path":"cifar/network-slimming/compute_flops.py","file_url":"https://github.com/Eric-mingjie/rethinking-network-pruning/blob/HEAD/cifar/network-slimming/compute_flops.py","link_basis":"harvester_set","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":"dbcc7f02b0356238"}},{"code_sha256_prefix":"929c091d6fd3e526","entry":"print_model_param_nums","repo":"Eric-mingjie/rethinking-network-pruning","repo_kind":"found_in_text","path":"cifar/network-slimming/compute_flops.py","file_url":"https://github.com/Eric-mingjie/rethinking-network-pruning/blob/HEAD/cifar/network-slimming/compute_flops.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":"929c091d6fd3e526"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}