{"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/pruning-neural-networks-with-interpolative","title":"Model Preserving Compression for Neural Networks","arxiv_id":"2108.00065","date":"2021-07-30","proceeding":null,"authors":["Jerry Chee","Megan Renz","Anil Damle","Christopher De Sa"],"abstract":"After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1 accuracy or preserve robustness), maintain the network's structure, automatically determine per-layer compression levels, and eliminate the need for fine tuning. No existing compression methods simultaneously satisfy these criteria $\\unicode{x2014}$ we introduce a principled approach that does by leveraging interpolative decompositions. Our approach simultaneously selects and eliminates channels (analogously, neurons), then constructs an interpolation matrix that propagates a correction into the next layer, preserving the network's structure. Consequently, our method achieves good performance even without fine tuning and admits theoretical analysis. Our theoretical generalization bound for a one layer network lends itself naturally to a heuristic that allows our method to automatically choose per-layer sizes for deep networks. We demonstrate the efficacy of our approach with strong empirical performance on a variety of tasks, models, and datasets $\\unicode{x2014}$ from simple one-hidden-layer networks to deep networks on ImageNet.","url_abs":"https://arxiv.org/abs/2108.00065v2","url_pdf":"https://arxiv.org/pdf/2108.00065v2.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":"pruning-neural-networks-with-interpolative","repo_url":"https://github.com/jerry-chee/modelpreservecompressionnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"},{"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=2108.00065","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}