{"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/fast-convex-pruning-of-deep-neural-networks","title":"Fast Convex Pruning of Deep Neural Networks","arxiv_id":"1806.06457","date":"2018-06-17","proceeding":null,"authors":["Alireza Aghasi","Afshin Abdi","Justin Romberg"],"abstract":"We develop a fast, tractable technique called Net-Trim for simplifying a\ntrained neural network. The method is a convex post-processing module, which\nprunes (sparsifies) a trained network layer by layer, while preserving the\ninternal responses. We present a comprehensive analysis of Net-Trim from both\nthe algorithmic and sample complexity standpoints, centered on a fast, scalable\nconvex optimization program. Our analysis includes consistency results between\nthe initial and retrained models before and after Net-Trim application and\nguarantees on the number of training samples needed to discover a network that\ncan be expressed using a certain number of nonzero terms. Specifically, if\nthere is a set of weights that uses at most $s$ terms that can re-create the\nlayer outputs from the layer inputs, we can find these weights from\n$\\mathcal{O}(s\\log N/s)$ samples, where $N$ is the input size. These\ntheoretical results are similar to those for sparse regression using the Lasso,\nand our analysis uses some of the same recently-developed tools (namely recent\nresults on the concentration of measure and convex analysis). Finally, we\npropose an algorithmic framework based on the alternating direction method of\nmultipliers (ADMM), which allows a fast and simple implementation of Net-Trim\nfor network pruning and compression.","url_abs":"http://arxiv.org/abs/1806.06457v2","url_pdf":"http://arxiv.org/pdf/1806.06457v2.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":"fast-convex-pruning-of-deep-neural-networks","repo_url":"https://github.com/DNNToolBox/Net-Trim-v1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.06457","atlas_url":"https://app.syntology.ai/?focus=1806.06457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.06457"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DNNToolBox/Net-Trim-v1","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":1,"samples":[{"code_sha256_prefix":"61bc458b7e6ef9a8","entry":"net_trim_solver_np","repo":"DNNToolBox/Net-Trim-v1","repo_kind":"listed","path":"NetTrimSolver.py","file_url":"https://github.com/DNNToolBox/Net-Trim-v1/blob/HEAD/NetTrimSolver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61bc458b7e6ef9a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}