{"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/loss-aware-weight-quantization-of-deep","title":"Loss-aware Weight Quantization of Deep Networks","arxiv_id":"1802.08635","date":"2018-02-23","proceeding":"ICLR 2018 1","authors":["Lu Hou","James T. Kwok"],"abstract":"The huge size of deep networks hinders their use in small computing devices.\nIn this paper, we consider compressing the network by weight quantization. We\nextend a recently proposed loss-aware weight binarization scheme to\nternarization, with possibly different scaling parameters for the positive and\nnegative weights, and m-bit (where m > 2) quantization. Experiments on\nfeedforward and recurrent neural networks show that the proposed scheme\noutperforms state-of-the-art weight quantization algorithms, and is as accurate\n(or even more accurate) than the full-precision network.","url_abs":"http://arxiv.org/abs/1802.08635v2","url_pdf":"http://arxiv.org/pdf/1802.08635v2.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":"loss-aware-weight-quantization-of-deep","repo_url":"https://github.com/houlu369/Loss-aware-weight-quantization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.08635","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}