{"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/spartan-differentiable-sparsity-via","title":"Spartan: Differentiable Sparsity via Regularized Transportation","arxiv_id":"2205.14107","date":"2022-05-27","proceeding":null,"authors":["Kai Sheng Tai","Taipeng Tian","Ser-Nam Lim"],"abstract":"We present Spartan, a method for training sparse neural network models with a predetermined level of sparsity. Spartan is based on a combination of two techniques: (1) soft top-k masking of low-magnitude parameters via a regularized optimal transportation problem and (2) dual averaging-based parameter updates with hard sparsification in the forward pass. This scheme realizes an exploration-exploitation tradeoff: early in training, the learner is able to explore various sparsity patterns, and as the soft top-k approximation is gradually sharpened over the course of training, the balance shifts towards parameter optimization with respect to a fixed sparsity mask. Spartan is sufficiently flexible to accommodate a variety of sparsity allocation policies, including both unstructured and block structured sparsity, as well as general cost-sensitive sparsity allocation mediated by linear models of per-parameter costs. On ImageNet-1K classification, Spartan yields 95% sparse ResNet-50 models and 90% block sparse ViT-B/16 models while incurring absolute top-1 accuracy losses of less than 1% compared to fully dense training.","url_abs":"https://arxiv.org/abs/2205.14107v2","url_pdf":"https://arxiv.org/pdf/2205.14107v2.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":"spartan-differentiable-sparsity-via","repo_url":"https://github.com/facebookresearch/spartan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/network-pruning-on-imagenet-resnet-50-90","task":"Network Pruning","dataset":"ImageNet - ResNet 50 - 90% sparsity","model":"Spartan","rank_in_archive_order":2,"of":9,"metrics":{"Top-1 Accuracy":"76.17"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14107","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}