{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:54Z","timestamp":1750219854344,"version":"3.41.0"},"reference-count":76,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Stanford Graduate Fellowship and a Meta research award"},{"name":"NSF GRFP, Stanford Graduate Fellowship"},{"name":"Two Sigma Diversity Ph.D. Fellowship"},{"name":"NSF","award":["#1651565, #1522054, #1733686"],"award-info":[{"award-number":["#1651565, #1522054, #1733686"]}]},{"name":"ONR","award":["N00014-19-1-2145"],"award-info":[{"award-number":["N00014-19-1-2145"]}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"crossref","award":["FA9550-19-1-0024"],"award-info":[{"award-number":["FA9550-19-1-0024"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ARO","award":["W911NF2110125"],"award-info":[{"award-number":["W911NF2110125"]}]},{"name":"Amazon AWS"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2023,5,31]]},"abstract":"<jats:p>\n            Compression and efficient storage of\n            <jats:bold>neural network (NN)<\/jats:bold>\n            parameters is critical for applications that run on resource-constrained devices. Despite the significant progress in NN model compression, there has been considerably less investigation in the actual\n            <jats:italic>physical<\/jats:italic>\n            storage of NN parameters. Conventionally, model compression and physical storage are decoupled, as digital storage media with\n            <jats:bold>error-correcting codes (ECCs)<\/jats:bold>\n            provide robust error-free storage. However, this decoupled approach is inefficient as it ignores the overparameterization present in most NNs and forces the memory device to allocate the same amount of resources to every bit of information regardless of its importance. In this work, we investigate analog memory devices as an alternative to digital media \u2013 one that naturally provides a way to add more protection for significant bits unlike its counterpart, but is noisy and may compromise the stored model\u2019s performance if used naively. We develop a variety of robust coding strategies for NN weight storage on analog devices, and propose an approach to jointly optimize model compression and memory resource allocation. We then demonstrate the efficacy of our approach on models trained on MNIST, CIFAR-10, and ImageNet datasets for existing compression techniques. Compared to conventional error-free digital storage, our method reduces the memory footprint by up to one order of magnitude, without significantly compromising the stored model\u2019s accuracy.\n          <\/jats:p>","DOI":"10.1145\/3588436","type":"journal-article","created":{"date-parts":[[2023,3,18]],"date-time":"2023-03-18T10:11:33Z","timestamp":1679134293000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Neural Network Compression for Noisy Storage Devices"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4926-5443","authenticated-orcid":false,"given":"Berivan","family":"Isik","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5859-7060","authenticated-orcid":false,"given":"Kristy","family":"Choi","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1877-9430","authenticated-orcid":false,"given":"Xin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1099-691X","authenticated-orcid":false,"given":"Tsachy","family":"Weissman","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0039-2887","authenticated-orcid":false,"given":"Stefano","family":"Ermon","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0096-1472","authenticated-orcid":false,"given":"H.-S. Philip","family":"Wong","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2055-6754","authenticated-orcid":false,"given":"Armin","family":"Alaghi","sequence":"additional","affiliation":[{"name":"Reality Labs Research, Meta, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"key":"e_1_3_4_2_2","article-title":"Where is the information in a deep neural network?","author":"Achille Alessandro","year":"2019","unstructured":"Alessandro Achille, Giovanni Paolini, and Stefano Soatto. 2019. Where is the information in a deep neural network? arXiv preprint arXiv:1905.12213 (2019).","journal-title":"arXiv preprint arXiv:1905.12213"},{"key":"e_1_3_4_3_2","first-page":"5145","volume-title":"Advances in Neural Information Processing Systems","author":"Banner Ron","year":"2018","unstructured":"Ron Banner, Itay Hubara, Elad Hoffer, and Daniel Soudry. 2018. Scalable methods for 8-bit training of neural networks. In Advances in Neural Information Processing Systems. 5145\u20135153."},{"key":"e_1_3_4_4_2","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume":"32","author":"Banner Ron","year":"2019","unstructured":"Ron Banner, Yury Nahshan, and Daniel Soudry. 2019. Post training 4-bit quantization of convolutional networks for rapid-deployment. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_5_2","first-page":"None","volume-title":"Advances in Neural Information Processing Systems","author":"Barber David","year":"2003","unstructured":"David Barber and Felix V. Agakov. 2003. The IM algorithm: A variational approach to information maximization. In Advances in Neural Information Processing Systems. None."},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.3042094"},{"key":"e_1_3_4_7_2","article-title":"Precise neural network computation with imprecise analog devices","author":"Binas Jonathan","year":"2016","unstructured":"Jonathan Binas, Daniel Neil, Giacomo Indiveri, Shih-Chii Liu, and Michael Pfeiffer. 2016. Precise neural network computation with imprecise analog devices. arXiv preprint arXiv:1606.07786 (2016).","journal-title":"arXiv preprint arXiv:1606.07786"},{"key":"e_1_3_4_8_2","first-page":"1","volume-title":"2021 Picture Coding Symposium (PCS)","author":"Bird Thomas","year":"2021","unstructured":"Thomas Bird, Johannes Ball\u00e9, Saurabh Singh, and Philip A. Chou. 2021. 3D scene compression through entropy penalized neural representation functions. In 2021 Picture Coding Symposium (PCS). IEEE, 1\u20135."},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.860751"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSTIC.2019.8755642"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.327"},{"key":"e_1_3_4_14_2","first-page":"1182","volume-title":"International Conference on Machine Learning","author":"Choi Kristy","year":"2019","unstructured":"Kristy Choi, Kedar Tatwawadi, Aditya Grover, Tsachy Weissman, and Stefano Ermon. 2019. Neural joint source-channel coding. In International Conference on Machine Learning. PMLR, 1182\u20131192."},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2975903"},{"key":"e_1_3_4_16_2","first-page":"598","volume-title":"Optimal Brain Damage","author":"Cun Yann Le","year":"1990","unstructured":"Yann Le Cun, John S. Denker, and Sara A. Solla. 1990. Optimal Brain Damage. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 598\u2013605."},{"key":"e_1_3_4_17_2","first-page":"1223","volume-title":"Advances in Neural Information Processing Systems","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc\u2019Aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, et\u00a0al. 2012. Large scale distributed deep networks. In Advances in Neural Information Processing Systems. 1223\u20131231."},{"key":"e_1_3_4_18_2","volume-title":"CVPR09","author":"Deng J.","year":"2009","unstructured":"J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In CVPR09."},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"issue":"10","key":"e_1_3_4_20_2","first-page":"1811","article-title":"An analog neural network computing engine using CMOS-compatible charge-trap-transistor (CTT)","volume":"38","author":"Du Yuan","year":"2018","unstructured":"Yuan Du, Li Du, Xuefeng Gu, Jieqiong Du, X. Shawn Wang, Boyu Hu, Mingzhe Jiang, Xiaoliang Chen, Subramanian S. Iyer, and Mau-Chung Frank Chang. 2018. An analog neural network computing engine using CMOS-compatible charge-trap-transistor (CTT). IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 38, 10 (2018), 1811\u20131819.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_4_21_2","unstructured":"Gintare Karolina Dziugaite Gabriel Arpino and Daniel M. Roy. 2018. Towards generalization guarantees for SGD: Data-dependent PAC-bayes priors. (2018)."},{"key":"e_1_3_4_22_2","first-page":"29.4.1\u201329.4.4","volume-title":"2014 IEEE International Electron Devices Meeting","author":"Engel J. H.","year":"2014","unstructured":"J. H. Engel, S. B. Eryilmaz, S. Kim, M. BrightSky, C. Lam, H. Lung, B. A. Olshausen, and H. P. Wong. 2014. Capacity optimization of emerging memory systems: A Shannon-inspired approach to device characterization. In 2014 IEEE International Electron Devices Meeting. 29.4.1\u201329.4.4."},{"key":"e_1_3_4_23_2","article-title":"Benchmarking inference performance of deep learning models on analog devices","author":"Fagbohungbe Omobayode","year":"2020","unstructured":"Omobayode Fagbohungbe and Lijun Qian. 2020. Benchmarking inference performance of deep learning models on analog devices. arXiv preprint arXiv:2011.11840 (2020).","journal-title":"arXiv preprint arXiv:2011.11840"},{"key":"e_1_3_4_24_2","unstructured":"Angela Fan Pierre Stock Benjamin Graham Edouard Grave R\u00e9mi Gribonval Herv\u00e9 J\u00e9gou and Armand Joulin. 2020. Training with quantization noise for extreme model compression. (2020)."},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2017.2746342"},{"key":"e_1_3_4_26_2","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle and Michael Carbin. 2019. The lottery ticket hypothesis: Finding sparse, trainable neural networks. International Conference on Learning Representations (ICLR) (2019).","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"e_1_3_4_27_2","first-page":"573","volume-title":"International Conference on Machine Learning","author":"Grosse Roger","year":"2016","unstructured":"Roger Grosse and James Martens. 2016. A Kronecker-factored approximate Fisher matrix for convolution layers. In International Conference on Machine Learning. 573\u2013582."},{"key":"e_1_3_4_28_2","first-page":"1379","volume-title":"Advances in Neural Information Processing Systems","author":"Guo Yiwen","year":"2016","unstructured":"Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic network surgery for efficient DNNs. In Advances in Neural Information Processing Systems. 1379\u20131387."},{"key":"e_1_3_4_29_2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. International Conference on Learning Representations (ICLR) (2016).","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"e_1_3_4_30_2","first-page":"1135","volume-title":"Advances in Neural Information Processing Systems","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. In Advances in Neural Information Processing Systems. 1135\u20131143."},{"key":"e_1_3_4_31_2","first-page":"263","volume-title":"Proceedings of the 6th International Conference on Neural Information Processing Systems (NIPS\u201993)","author":"Hassibi Babak","year":"1993","unstructured":"Babak Hassibi, David G. Stork, Gregory Wolff, and Takahiro Watanabe. 1993. Optimal brain surgeon: Extensions and performance comparisons. In Proceedings of the 6th International Conference on Neural Information Processing Systems (NIPS\u201993). San Francisco, CA, USA, 263\u2013270."},{"key":"e_1_3_4_32_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Havasi Marton","year":"2019","unstructured":"Marton Havasi, Robert Peharz, and Jos\u00e9 Miguel Hern\u00e1ndez-Lobato. 2019. Minimal random code learning: Getting bits back from compressed model parameters. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_34_2","volume-title":"NIPS Deep Learning and Representation Learning Workshop","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the knowledge in a neural network. In NIPS Deep Learning and Representation Learning Workshop. http:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_4_35_2","article-title":"Characterising bias in compressed models","author":"Hooker Sara","year":"2020","unstructured":"Sara Hooker, Nyalleng Moorosi, Gregory Clark, Samy Bengio, and Emily Denton. 2020. Characterising bias in compressed models. arXiv preprint arXiv:2010.03058 (2020).","journal-title":"arXiv preprint arXiv:2010.03058"},{"key":"e_1_3_4_36_2","article-title":"Neural 3D scene compression via model compression","author":"Isik Berivan","year":"2021","unstructured":"Berivan Isik. 2021. Neural 3D scene compression via model compression. arXiv preprint arXiv:2105.03120 (2021).","journal-title":"arXiv preprint arXiv:2105.03120"},{"key":"e_1_3_4_37_2","first-page":"65","article-title":"LVAC: Learned volumetric attribute compression for point clouds using coordinate based networks","author":"Isik Berivan","year":"2021","unstructured":"Berivan Isik, Philip Chou, Sung Jin Hwang, Nicholas Johnston, and George Toderici. 2021. LVAC: Learned volumetric attribute compression for point clouds using coordinate based networks. Frontiers in Signal Processing (2021), 65.","journal-title":"Frontiers in Signal Processing"},{"key":"e_1_3_4_38_2","article-title":"Rate-distortion theoretic model compression: Successive refinement for pruning","author":"Isik Berivan","year":"2021","unstructured":"Berivan Isik, Albert No, and Tsachy Weissman. 2021. Rate-distortion theoretic model compression: Successive refinement for pruning. arXiv preprint arXiv:2102.08329 (2021).","journal-title":"arXiv preprint arXiv:2102.08329"},{"key":"e_1_3_4_39_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Isik Berivan","year":"2023","unstructured":"Berivan Isik, Francesco Pase, Deniz Gunduz, Tsachy Weissman, and Zorzi Michele. 2023. Sparse random networks for communication-efficient federated learning. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=k1FHgri5y3-"},{"key":"e_1_3_4_40_2","doi-asserted-by":"crossref","first-page":"1844","DOI":"10.1109\/ISIT50566.2022.9834601","volume-title":"2022 IEEE International Symposium on Information Theory (ISIT)","author":"Isik Berivan","year":"2022","unstructured":"Berivan Isik and Tsachy Weissman. 2022. Learning under storage and privacy constraints. In 2022 IEEE International Symposium on Information Theory (ISIT). IEEE, 1844\u20131849."},{"key":"e_1_3_4_41_2","first-page":"3821","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Isik Berivan","year":"2022","unstructured":"Berivan Isik, Tsachy Weissman, and Albert No. 2022. An information-theoretic justification for model pruning. In International Conference on Artificial Intelligence and Statistics. PMLR, 3821\u20133846."},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_4_43_2","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-16108-9","article-title":"Accurate deep neural network inference using computational phase-change memory","volume":"11","author":"Joshi V.","year":"2020","unstructured":"V. Joshi, M. Le Gallo, Simon Haefeli, I. Boybat, S. Nandakumar, C. Piveteau, M. Dazzi, B. Rajendran, A. Sebastian, and E. Eleftheriou. 2020. Accurate deep neural network inference using computational phase-change memory. Nature Communications 11 (2020).","journal-title":"Nature Communications"},{"key":"e_1_3_4_44_2","volume-title":"International Conference on Learning Representations","author":"Khoram Soroosh","year":"2018","unstructured":"Soroosh Khoram and Jing Li. 2018. Adaptive quantization of neural networks. In International Conference on Learning Representations."},{"key":"e_1_3_4_45_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431542"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_4_49_2","unstructured":"Yann LeCun Corinna Cortes and C. J. Burges. 2010. MNIST handwritten digit database. (2010)."},{"key":"e_1_3_4_50_2","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"Lee Namhoon","year":"2018","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, and Philip H. S. Torr. 2018. SNIP: Single-shot network pruning based on connection sensitivity. arXiv preprint arXiv:1810.02340 (2018).","journal-title":"arXiv preprint arXiv:1810.02340"},{"key":"e_1_3_4_51_2","article-title":"Bayesian compression for deep learning","author":"Louizos Christos","year":"2017","unstructured":"Christos Louizos, Karen Ullrich, and Max Welling. 2017. Bayesian compression for deep learning. arXiv preprint arXiv:1705.08665 (2017).","journal-title":"arXiv preprint arXiv:1705.08665"},{"key":"e_1_3_4_52_2","article-title":"New insights and perspectives on the natural gradient method","author":"Martens James","year":"2014","unstructured":"James Martens. 2014. New insights and perspectives on the natural gradient method. arXiv preprint arXiv:1412.1193 (2014).","journal-title":"arXiv preprint arXiv:1412.1193"},{"key":"e_1_3_4_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS46596.2019.8964852"},{"key":"e_1_3_4_55_2","article-title":"Scalable model compression by entropy penalized reparameterization","author":"Oktay Deniz","year":"2019","unstructured":"Deniz Oktay, Johannes Ball\u00e9, Saurabh Singh, and Abhinav Shrivastava. 2019. Scalable model compression by entropy penalized reparameterization. arXiv preprint arXiv:1906.06624 (2019).","journal-title":"arXiv preprint arXiv:1906.06624"},{"key":"e_1_3_4_56_2","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/SP.2016.41","volume-title":"2016 IEEE Symposium on Security and Privacy (SP)","author":"Papernot Nicolas","year":"2016","unstructured":"Nicolas Papernot, Patrick McDaniel, Xi Wu, Somesh Jha, and Ananthram Swami. 2016. Distillation as a defense to adversarial perturbations against deep neural networks. In 2016 IEEE Symposium on Security and Privacy (SP). IEEE, 582\u2013597."},{"volume-title":"Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022)","author":"Pase Francesco","key":"e_1_3_4_57_2","unstructured":"Francesco Pase, Berivan Isik, Deniz Gunduz, Tsachy Weissman, and Michele Zorzi. [n. d.]. Efficient federated random subnetwork training. In Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022)."},{"key":"e_1_3_4_58_2","article-title":"Model compression via distillation and quantization","author":"Polino Antonio","year":"2018","unstructured":"Antonio Polino, Razvan Pascanu, and Dan Alistarh. 2018. Model compression via distillation and quantization. arXiv preprint arXiv:1802.05668 (2018).","journal-title":"arXiv preprint arXiv:1802.05668"},{"key":"e_1_3_4_59_2","first-page":"4324","volume-title":"International Conference on Machine Learning","author":"Reagan Brandon","year":"2018","unstructured":"Brandon Reagan, Udit Gupta, Bob Adolf, Michael Mitzenmacher, Alexander Rush, Gu-Yeon Wei, and David Brooks. 2018. Weightless: Lossy weight encoding for deep neural network compression. In International Conference on Machine Learning. 4324\u20134333."},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_4_61_2","doi-asserted-by":"publisher","DOI":"10.1049\/ip-cds:19990685"},{"key":"e_1_3_4_62_2","article-title":"Hydra: Pruning adversarially robust neural networks","volume":"7","author":"Sehwag Vikash","year":"2020","unstructured":"Vikash Sehwag, Shiqi Wang, Prateek Mittal, and Suman Jana. 2020. Hydra: Pruning adversarially robust neural networks. Advances in Neural Information Processing Systems (NeurIPS) 7 (2020).","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"issue":"1","key":"e_1_3_4_63_2","article-title":"A mathematical theory of communication","volume":"5","author":"Shannon Claude Elwood","year":"2001","unstructured":"Claude Elwood Shannon. 2001. A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review 5, 1 (2001).","journal-title":"ACM SIGMOBILE Mobile Computing and Communications Review"},{"key":"e_1_3_4_64_2","article-title":"WoodFisher: Efficient second-order approximations for model compression","author":"Singh Sidak Pal","year":"2020","unstructured":"Sidak Pal Singh and Dan Alistarh. 2020. WoodFisher: Efficient second-order approximations for model compression. arXiv preprint arXiv:2004.14340 (2020).","journal-title":"arXiv preprint arXiv:2004.14340"},{"key":"e_1_3_4_65_2","first-page":"6105","volume-title":"International Conference on Machine Learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. PMLR, 6105\u20136114."},{"key":"e_1_3_4_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2012.081012.110010"},{"key":"e_1_3_4_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2969554"},{"key":"e_1_3_4_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2070050"},{"key":"e_1_3_4_69_2","first-page":"27","volume-title":"2018 IEEE International Electron Devices Meeting (IEDM)","author":"Wu J. Y.","year":"2018","unstructured":"J. Y. Wu, Y. S. Chen, W. S. Khwa, S. M. Yu, T. Y. Wang, J. C. Tseng, Y. D. Chih, and Carlos H. Diaz. 2018. A 40nm low-power logic compatible phase change memory technology. In 2018 IEEE International Electron Devices Meeting (IEDM). IEEE, 27\u20136."},{"key":"e_1_3_4_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"e_1_3_4_71_2","article-title":"Transform quantization for CNN compression","author":"Young Sean I.","year":"2020","unstructured":"Sean I. Young, Wang Zhe, David Taubman, and Bernd Girod. 2020. Transform quantization for CNN compression. arXiv preprint arXiv:2009.01174 (2020).","journal-title":"arXiv preprint arXiv:2009.01174"},{"key":"e_1_3_4_72_2","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/DCC.2018.00023","volume-title":"2018 Data Compression Conference","author":"Zarcone Ryan","year":"2018","unstructured":"Ryan Zarcone, Dylan Paiton, Alex Anderson, Jesse Engel, H. S. Philip Wong, and Bruno Olshausen. 2018. Joint source-channel coding with neural networks for analog data compression and storage. In 2018 Data Compression Conference. IEEE, 147\u2013156."},{"key":"e_1_3_4_73_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-70121-y"},{"key":"e_1_3_4_74_2","first-page":"3","volume-title":"2018 IEEE International Electron Devices Meeting (IEDM)","author":"Zheng Xin","year":"2018","unstructured":"Xin Zheng, Ryan Zarcone, Dylan Paiton, Joon Sohn, Weier Wan, Bruno Olshausen, and H.-S. Philip Wong. 2018. Error-resilient analog image storage and compression with analog-valued RRAM arrays: An adaptive joint source-channel coding approach. In 2018 IEEE International Electron Devices Meeting (IEDM). IEEE, 3\u20135."},{"key":"e_1_3_4_75_2","article-title":"Noisy machines: Understanding noisy neural networks and enhancing robustness to analog hardware errors using distillation","author":"Zhou Chuteng","year":"2020","unstructured":"Chuteng Zhou, Prad Kadambi, Matthew Mattina, and Paul N. Whatmough. 2020. Noisy machines: Understanding noisy neural networks and enhancing robustness to analog hardware errors using distillation. arXiv preprint arXiv:2001.04974 (2020).","journal-title":"arXiv preprint arXiv:2001.04974"},{"key":"e_1_3_4_76_2","article-title":"Information contraction in noisy binary neural networks and its implications","author":"Zhou Chuteng","year":"2021","unstructured":"Chuteng Zhou, Quntao Zhuang, Matthew Mattina, and Paul N. Whatmough. 2021. Information contraction in noisy binary neural networks and its implications. arXiv preprint arXiv:2101.11750 (2021).","journal-title":"arXiv preprint arXiv:2101.11750"},{"key":"e_1_3_4_77_2","article-title":"Non-vacuous generalization bounds at the ImageNet scale: A PAC-Bayesian compression approach","author":"Zhou Wenda","year":"2018","unstructured":"Wenda Zhou, Victor Veitch, Morgane Austern, Ryan P. Adams, and Peter Orbanz. 2018. Non-vacuous generalization bounds at the ImageNet scale: A PAC-Bayesian compression approach. arXiv preprint arXiv:1804.05862 (2018).","journal-title":"arXiv preprint arXiv:1804.05862"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588436","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:12Z","timestamp":1750178832000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":76,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,5,31]]}},"alternative-id":["10.1145\/3588436"],"URL":"https:\/\/doi.org\/10.1145\/3588436","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2023,5,13]]},"assertion":[{"value":"2022-03-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}