{"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/soft-weight-sharing-for-neural-network","title":"Soft Weight-Sharing for Neural Network Compression","arxiv_id":"1702.04008","date":"2017-02-13","proceeding":null,"authors":["Karen Ullrich","Edward Meeds","Max Welling"],"abstract":"The success of deep learning in numerous application domains created the de-\nsire to run and train them on mobile devices. This however, conflicts with\ntheir computationally, memory and energy intense nature, leading to a growing\ninterest in compression. Recent work by Han et al. (2015a) propose a pipeline\nthat involves retraining, pruning and quantization of neural network weights,\nobtaining state-of-the-art compression rates. In this paper, we show that\ncompetitive compression rates can be achieved by using a version of soft\nweight-sharing (Nowlan & Hinton, 1992). Our method achieves both quantization\nand pruning in one simple (re-)training procedure. This point of view also\nexposes the relation between compression and the minimum description length\n(MDL) principle.","url_abs":"http://arxiv.org/abs/1702.04008v2","url_pdf":"http://arxiv.org/pdf/1702.04008v2.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":"soft-weight-sharing-for-neural-network","repo_url":"https://github.com/KarenUllrich/Tutorial-SoftWeightSharingForNNCompression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"soft-weight-sharing-for-neural-network","repo_url":"https://github.com/KarenUllrich/Tutorial_BayesianCompressionForDL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-weight-sharing-for-neural-network","repo_url":"https://github.com/akashrajkn/waffles-and-posteriors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"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=1702.04008","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}