{"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/rotation-invariant-quantization-for-model","title":"Rotation Invariant Quantization for Model Compression","arxiv_id":"2303.03106","date":"2023-03-03","proceeding":null,"authors":["Joseph Kampeas","Yury Nahshan","Hanoch Kremer","Gil Lederman","Shira Zaloshinski","Zheng Li","Emir Haleva"],"abstract":"Post-training Neural Network (NN) model compression is an attractive approach for deploying large, memory-consuming models on devices with limited memory resources. In this study, we investigate the rate-distortion tradeoff for NN model compression. First, we suggest a Rotation-Invariant Quantization (RIQ) technique that utilizes a single parameter to quantize the entire NN model, yielding a different rate at each layer, i.e., mixed-precision quantization. Then, we prove that our rotation-invariant approach is optimal in terms of compression. We rigorously evaluate RIQ and demonstrate its capabilities on various models and tasks. For example, RIQ facilitates $\\times 19.4$ and $\\times 52.9$ compression ratios on pre-trained VGG dense and pruned models, respectively, with $<0.4\\%$ accuracy degradation. Code is available in \\href{https://github.com/ehaleva/RIQ}{github.com/ehaleva/RIQ}.","url_abs":"https://arxiv.org/abs/2303.03106v3","url_pdf":"https://arxiv.org/pdf/2303.03106v3.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":"rotation-invariant-quantization-for-model","repo_url":"https://github.com/ehaleva/riq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.03106","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}