{"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/weightless-lossy-weight-encoding-for-deep","title":"Weightless: Lossy Weight Encoding For Deep Neural Network Compression","arxiv_id":"1711.04686","date":"2017-11-13","proceeding":null,"authors":["Brandon Reagen","Udit Gupta","Robert Adolf","Michael M. Mitzenmacher","Alexander M. Rush","Gu-Yeon Wei","David Brooks"],"abstract":"The large memory requirements of deep neural networks limit their deployment\nand adoption on many devices. Model compression methods effectively reduce the\nmemory requirements of these models, usually through applying transformations\nsuch as weight pruning or quantization. In this paper, we present a novel\nscheme for lossy weight encoding which complements conventional compression\ntechniques. The encoding is based on the Bloomier filter, a probabilistic data\nstructure that can save space at the cost of introducing random errors.\nLeveraging the ability of neural networks to tolerate these imperfections and\nby re-training around the errors, the proposed technique, Weightless, can\ncompress DNN weights by up to 496x with the same model accuracy. This results\nin up to a 1.51x improvement over the state-of-the-art.","url_abs":"http://arxiv.org/abs/1711.04686v1","url_pdf":"http://arxiv.org/pdf/1711.04686v1.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":"weightless-lossy-weight-encoding-for-deep","repo_url":"https://github.com/cambridge-mlg/miracle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"weightless-lossy-weight-encoding-for-deep","repo_url":"https://github.com/cambridge-mlg/variational-shannon-coding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"neural-network-compression","task_name":"Neural Network Compression"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.04686","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}