{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:33:20Z","timestamp":1772724800469,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":84,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0110104"],"award-info":[{"award-number":["2021ZD0110104"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62222210"],"award-info":[{"award-number":["62222210"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["U21B2017"],"award-info":[{"award-number":["U21B2017"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["61832006"],"award-info":[{"award-number":["61832006"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62072297"],"award-info":[{"award-number":["62072297"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3617232.3624864","type":"proceedings-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T20:10:56Z","timestamp":1713384656000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Amanda: Unified Instrumentation Framework for Deep Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7433-2627","authenticated-orcid":false,"given":"Yue","family":"Guan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"},{"name":"Shanghai Qi Zhi Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4040-0159","authenticated-orcid":false,"given":"Yuxian","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"},{"name":"Shanghai Qi Zhi Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5660-5493","authenticated-orcid":false,"given":"Jingwen","family":"Leng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"},{"name":"Shanghai Qizhi Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0378-060X","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5474-6954","authenticated-orcid":false,"given":"Shuo","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7352-8955","authenticated-orcid":false,"given":"Yunxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"},{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2192-5737","authenticated-orcid":false,"given":"Yu","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Rochester, New York, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2802-0578","authenticated-orcid":false,"given":"Yuhao","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Rochester, New York, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7258-3116","authenticated-orcid":false,"given":"Lidong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-7998","authenticated-orcid":false,"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2762-2726","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6218-4659","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2019. NVIDIA APEX. https:\/\/github.com\/NVIDIA\/apex."},{"key":"e_1_3_2_1_2_1","unstructured":"2021. TorchProfile. https:\/\/github.com\/zhijian-liu\/torchprofile."},{"key":"e_1_3_2_1_3_1","unstructured":"2022. OneFlow OpCounter. https:\/\/github.com\/Oneflow-Inc\/flow-OpCounter."},{"key":"e_1_3_2_1_4_1","unstructured":"2023. TensorBoard. https:\/\/tensorboard.dev\/."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. CUDA Profiling Tools Interface. https:\/\/docs.nvidia.com\/cupti\/."},{"key":"e_1_3_2_1_6_1","unstructured":"2023. TensorFlow Profiler. https:\/\/github.com\/tensorflow\/profiler."},{"key":"e_1_3_2_1_7_1","unstructured":"2023. Torch Profiler. https:\/\/pytorch.org\/docs\/stable\/profiler.html."},{"key":"e_1_3_2_1_8_1","unstructured":"2023. TorchDynamo. https:\/\/github.com\/pytorch\/torchdynamo."},{"key":"e_1_3_2_1_9_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro GregS. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of machine learning and systems 2","author":"Blalock Davis","year":"2020","unstructured":"Davis Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John Guttag. 2020. What is the state of neural network pruning? Proceedings of machine learning and systems 2 (2020), 129--146."},{"key":"e_1_3_2_1_12_1","volume-title":"Deep Learning and Practice with MindSpore","author":"Chen Lei","unstructured":"Lei Chen. 2021. Deep Learning and Practice with MindSpore. Springer Nature."},{"key":"e_1_3_2_1_13_1","volume-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274","author":"Chen Tianqi","year":"2015","unstructured":"Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. 2015. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015)."},{"key":"e_1_3_2_1_14_1","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze et al. 2018. {TVM}: An automated end-to-end optimizing compiler for deep learning. In 13th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 18). 578--594."},{"key":"e_1_3_2_1_15_1","volume-title":"Training Deep Nets with Sublinear Memory Cost. CoRR abs\/1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training Deep Nets with Sublinear Memory Cost. CoRR abs\/1604.06174 (2016). arXiv:1604.06174 http:\/\/arxiv.org\/abs\/1604.06174"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_18_1","unstructured":"ONNX Runtime developers. 2021. ONNX Runtime. https:\/\/onnxruntime.ai\/. Version: x.y.z."},{"key":"e_1_3_2_1_19_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Dong Xuanyi","year":"2019","unstructured":"Xuanyi Dong and Yi Yang. 2019. Network Pruning via Transformable Architecture Search. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8--14 December 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 759--770. http:\/\/papers.nips.cc\/paper\/8364-network-pruning-via-transformable-architecture-search"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.110"},{"key":"e_1_3_2_1_22_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_23_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Esser Steven K.","year":"2020","unstructured":"Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S. Modha. 2020. Learned Step Size quantization. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=rkgO66VKDS"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00031"},{"key":"e_1_3_2_1_26_1","volume-title":"Dynamic channel pruning: Feature boosting and suppression. arXiv preprint arXiv:1810.05331","author":"Gao Xitong","year":"2018","unstructured":"Xitong Gao, Yiren Zhao, \u0141ukasz Dudziak, Robert Mullins, and Chengzhong Xu. 2018. Dynamic channel pruning: Feature boosting and suppression. arXiv preprint arXiv:1810.05331 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.07.007"},{"key":"e_1_3_2_1_28_1","volume-title":"A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630","author":"Gholami Amir","year":"2021","unstructured":"Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W Mahoney, and Kurt Keutzer. 2021. A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630 (2021)."},{"key":"e_1_3_2_1_29_1","unstructured":"Andreas Griewank et al. 1989. On automatic differentiation. Mathematical Programming: recent developments and applications 6 6 (1989) 83--107."},{"key":"e_1_3_2_1_30_1","volume-title":"How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT' s Attention. arXiv preprint arXiv:2011.00943","author":"Guan Yue","year":"2020","unstructured":"Yue Guan, Jingwen Leng, Chao Li, Quan Chen, and Minyi Guo. 2020. How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT' s Attention. arXiv preprint arXiv:2011.00943 (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.502"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21316"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433722"},{"key":"e_1_3_2_1_34_1","volume-title":"SQuant: On-the-fly data-free quantization via diagonal hessian approximation. arXiv preprint arXiv:2202.07471","author":"Guo Cong","year":"2022","unstructured":"Cong Guo, Yuxian Qiu, Jingwen Leng, Xiaotian Gao, Chen Zhang, Yunxin Liu, Fan Yang, Yuhao Zhu, and Minyi Guo. 2022. SQuant: On-the-fly data-free quantization via diagonal hessian approximation. arXiv preprint arXiv:2202.07471 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training. In 2022 IEEE 40th International Conference on Computer Design (ICCD). IEEE, 738--745","author":"Guo Cong","year":"2022","unstructured":"Cong Guo, Yuxian Qiu, Jingwen Leng, Chen Zhang, Ying Cao, Quanlu Zhang, Yunxin Liu, Fan Yang, and Minyi Guo. 2022. Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training. In 2022 IEEE 40th International Conference on Computer Design (ICCD). IEEE, 738--745."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"},{"key":"e_1_3_2_1_38_1","volume-title":"Dynamic Network Surgery for Efficient DNNs. CoRR abs\/1608.04493","author":"Guo Yiwen","year":"2016","unstructured":"Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic Network Surgery for Efficient DNNs. CoRR abs\/1608.04493 (2016). arXiv:1608.04493 http:\/\/arxiv.org\/abs\/1608.04493"},{"key":"e_1_3_2_1_39_1","unstructured":"Sean Hallgren. 1994. Linear congruential generators over elliptic curves. Citeseer."},{"key":"e_1_3_2_1_40_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_41_1","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--1143."},{"key":"e_1_3_2_1_42_1","volume-title":"Dynamic neural networks: A survey","author":"Han Yizeng","year":"2021","unstructured":"Yizeng Han, Gao Huang, Shiji Song, Le Yang, Honghui Wang, and Yulin Wang. 2021. Dynamic neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_1_46_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Hooker Sara","year":"2019","unstructured":"Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, and Been Kim. 2019. A Benchmark for Interpretability Methods in Deep Neural Networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 9734--9745. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/fe4b8556000d0f0cae99daa5c5c5a410-Abstract.html"},{"key":"e_1_3_2_1_47_1","volume-title":"Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146","author":"Howard Jeremy","year":"2018","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)."},{"key":"e_1_3_2_1_48_1","volume-title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. CoRR abs\/1712.05877","author":"Jacob Benoit","year":"2017","unstructured":"Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew G. Howard, Hartwig Adam, and Dmitry Kalenichenko. 2017. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. CoRR abs\/1712.05877 (2017). arXiv:1712.05877 http:\/\/arxiv.org\/abs\/1712.05877"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of Machine Learning and Systems 2020","author":"Jain Sambhav R.","year":"2020","unstructured":"Sambhav R. Jain, Albert Gural, Michael Wu, and Chris Dick. 2020. Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks. In Proceedings of Machine Learning and Systems 2020, MLSys 2020, Austin, TX, USA, March 2--4, 2020, Inderjit S. Dhillon, Dimitris S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/book\/295.pdf"},{"key":"e_1_3_2_1_50_1","volume-title":"Dynamic Tensor Rematerialization. In 9th International Conference on Learning Representations, ICLR 2021","author":"Kirisame Marisa","year":"2021","unstructured":"Marisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, Tianqi Chen, and Zachary Tatlock. 2021. Dynamic Tensor Rematerialization. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=Vfs_2RnOD0H"},{"key":"e_1_3_2_1_51_1","unstructured":"Yann LeCun John S Denker and Sara A Solla. 1990. Optimal brain damage. In Advances in neural information processing systems. 598--605."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507752"},{"key":"e_1_3_2_1_53_1","volume-title":"Rethinking the Value of Network Pruning. CoRR abs\/1810.05270","author":"Liu Zhuang","year":"2018","unstructured":"Zhuang Liu, Mingjie Sun, Tinghui Zhou, Gao Huang, and Trevor Darrell. 2018. Rethinking the Value of Network Pruning. CoRR abs\/1810.05270 (2018). arXiv:1810.05270 http:\/\/arxiv.org\/abs\/1810.05270"},{"key":"e_1_3_2_1_54_1","volume-title":"Vijay Janapa Reddi, and Kim Hazelwood","author":"Luk Chi-Keung","year":"2005","unstructured":"Chi-Keung Luk, Robert Cohn, Robert Muth, Harish Patil, Artur Klauser, Geoff Lowney, Steven Wallace, Vijay Janapa Reddi, and Kim Hazelwood. 2005. Pin: building customized program analysis tools with dynamic instrumentation. Acm sigplan notices 40, 6 (2005), 190--200."},{"key":"e_1_3_2_1_55_1","volume-title":"Adversarial Neural Pruning. CoRR abs\/1908.04355","author":"Madaan Divyam","year":"2019","unstructured":"Divyam Madaan and Sung Ju Hwang. 2019. Adversarial Neural Pruning. CoRR abs\/1908.04355 (2019). arXiv:1908.04355 http:\/\/arxiv.org\/abs\/1908.04355"},{"key":"e_1_3_2_1_56_1","volume-title":"Are Sixteen Heads Really Better than One? arXiv preprint arXiv:1905.10650","author":"Michel Paul","year":"2019","unstructured":"Paul Michel, Omer Levy, and Graham Neubig. 2019. Are Sixteen Heads Really Better than One? arXiv preprint arXiv:1905.10650 (2019)."},{"key":"e_1_3_2_1_57_1","unstructured":"Microsoft. 2021. Neural Network Intelligence. https:\/\/github.com\/microsoft\/nni"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573521"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_36"},{"key":"e_1_3_2_1_60_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_1_61_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019), 8026--8037."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00491"},{"key":"e_1_3_2_1_64_1","volume-title":"100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)."},{"key":"e_1_3_2_1_65_1","first-page":"638","article-title":"Torch. fx: Practical program capture and transformation for deep learning in python","volume":"4","author":"Reed James","year":"2022","unstructured":"James Reed, Zachary DeVito, Horace He, Ansley Ussery, and Jason Ansel. 2022. Torch. fx: Practical program capture and transformation for deep learning in python. Proceedings of Machine Learning and Systems 4 (2022), 638--651.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_66_1","volume-title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning. arXiv preprint arXiv:2003.02389","author":"Renda Alex","year":"2020","unstructured":"Alex Renda, Jonathan Frankle, and Michael Carbin. 2020. Comparing Rewinding and Fine-tuning in Neural Network Pruning. arXiv preprint arXiv:2003.02389 (2020)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2021.114135"},{"key":"e_1_3_2_1_68_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_69_1","volume-title":"Megan Leszczynski, Jian Zhang, and Christopher R\u00e9.","author":"Sohoni Nimit Sharad","year":"2019","unstructured":"Nimit Sharad Sohoni, Christopher Richard Aberger, Megan Leszczynski, Jian Zhang, and Christopher R\u00e9. 2019. Low-memory neural network training: A technical report. arXiv preprint arXiv:1904.10631 (2019)."},{"key":"e_1_3_2_1_70_1","unstructured":"Vladislav Sovrasov. 2018--2023. ptflops: a flops counting tool for neural networks in pytorch framework. https:\/\/github.com\/sovrasov\/flops-counter.pytorch"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358307"},{"key":"e_1_3_2_1_75_1","first-page":"11960","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","volume":"34","author":"Wang Yulin","year":"2021","unstructured":"Yulin Wang, Rui Huang, Shiji Song, Zeyi Huang, and Gao Huang. 2021. Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition. Advances in Neural Information Processing Systems 34 (2021), 11960--11973.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_76_1","volume-title":"Pruning from Scratch. CoRR abs\/1909.12579","author":"Wang Yulong","year":"2019","unstructured":"Yulong Wang, Xiaolu Zhang, Lingxi Xie, Jun Zhou, Hang Su, Bo Zhang, and Xiaolin Hu. 2019. Pruning from Scratch. CoRR abs\/1909.12579 (2019). arXiv:1909.12579 http:\/\/arxiv.org\/abs\/1909.12579"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015676"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3178115","article-title":"Deep learning for environmentally robust speech recognition: An overview of recent developments","volume":"9","author":"Zhang Zixing","year":"2018","unstructured":"Zixing Zhang, J\u00fcrgen Geiger, Jouni Pohjalainen, Amr El-Desoky Mousa, Wenyu Jin, and Bj\u00f6rn Schuller. 2018. Deep learning for environmentally robust speech recognition: An overview of recent developments. ACM Transactions on Intelligent Systems and Technology (TIST) 9, 5 (2018), 1--28.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"e_1_3_2_1_80_1","volume-title":"Learning n: m fine-grained structured sparse neural networks from scratch. arXiv preprint arXiv:2102.04010","author":"Zhou Aojun","year":"2021","unstructured":"Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, and Hongsheng Li. 2021. Learning n: m fine-grained structured sparse neural networks from scratch. arXiv preprint arXiv:2102.04010 (2021)."},{"key":"e_1_3_2_1_81_1","volume-title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. CoRR abs\/1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Zekun Ni, Xinyu Zhou, He Wen, Yuxin Wu, and Yuheng Zou. 2016. DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. CoRR abs\/1606.06160 (2016). arXiv:1606.06160 http:\/\/arxiv.org\/abs\/1606.06160"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575723"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00029"},{"key":"e_1_3_2_1_84_1","volume-title":"Daydream: Accurately Estimating the Efficacy of Optimizations for {DNN} Training. In 2020 {USENIX} Annual Technical Conference ({USENIX}{ATC} 20). 337--352.","author":"Zhu Hongyu","year":"2020","unstructured":"Hongyu Zhu, Amar Phanishayee, and Gennady Pekhimenko. 2020. Daydream: Accurately Estimating the Efficacy of Optimizations for {DNN} Training. In 2020 {USENIX} Annual Technical Conference ({USENIX}{ATC} 20). 337--352."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617232.3624864","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617232.3624864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:14Z","timestamp":1750178774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617232.3624864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":84,"alternative-id":["10.1145\/3617232.3624864","10.1145\/3617232"],"URL":"https:\/\/doi.org\/10.1145\/3617232.3624864","relation":{},"subject":[],"published":{"date-parts":[[2024,4,17]]},"assertion":[{"value":"2024-04-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}