{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:36:46Z","timestamp":1772937406507,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MIT-IBM Watson AI Lab, MIT AI Hardware Program, MIT-Amazon Science Hub, NSF"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,28]]},"DOI":"10.1145\/3613424.3614307","type":"proceedings-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T17:22:15Z","timestamp":1702056135000},"page":"1381-1394","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["PockEngine: Sparse and Efficient Fine-tuning in a Pocket"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6969-1706","authenticated-orcid":false,"given":"Ligeng","family":"Zhu","sequence":"first","affiliation":[{"name":"EECS, MIT, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0641-3677","authenticated-orcid":false,"given":"Lanxiang","family":"Hu","sequence":"additional","affiliation":[{"name":"UCSD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6053-4344","authenticated-orcid":false,"given":"Ji","family":"Lin","sequence":"additional","affiliation":[{"name":"EECS, MIT, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7177-4167","authenticated-orcid":false,"given":"Wei-Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"EECS, MIT, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9435-6598","authenticated-orcid":false,"given":"Wei-Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"EECS, MIT, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4031-5886","authenticated-orcid":false,"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[{"name":"EECS, MIT-IBM Watson AI Lab, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-7618","authenticated-orcid":false,"given":"Song","family":"Han","sequence":"additional","affiliation":[{"name":"EECS, MIT, USA and NVIDIA, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,12,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. NCNN : A high-performance neural network inference computing framework optimized for mobile platforms. https:\/\/github.com\/Tencent\/ncnn.  [n. d.]. NCNN : A high-performance neural network inference computing framework optimized for mobile platforms. https:\/\/github.com\/Tencent\/ncnn."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. NVIDIA TensorRT an SDK for high-performance deep learning inference. https:\/\/developer.nvidia.com\/tensorrt.  [n. d.]. NVIDIA TensorRT an SDK for high-performance deep learning inference. https:\/\/developer.nvidia.com\/tensorrt."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. TensorFlow Lite Micro.  [n. d.]. TensorFlow Lite Micro."},{"key":"e_1_3_2_1_4_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg\u00a0S. 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.  Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg\u00a0S. 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_5_1","volume-title":"Tensorflow: A system for large-scale machine learning. In OSDI.","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi , Paul Barham , Jianmin Chen , Zhifeng Chen , Andy Davis , Jeffrey Dean , Matthieu Devin , Sanjay Ghemawat , Geoffrey Irving , Michael Isard , 2016 . Tensorflow: A system for large-scale machine learning. In OSDI. Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, 2016. Tensorflow: A system for large-scale machine learning. In OSDI."},{"key":"e_1_3_2_1_6_1","volume-title":"Ordering chaos: Memory-aware scheduling of irregularly wired neural networks for edge devices. arXiv preprint arXiv:2003.02369","author":"Ahn Byung\u00a0Hoon","year":"2020","unstructured":"Byung\u00a0Hoon Ahn , Jinwon Lee , Jamie\u00a0Menjay Lin , Hsin-Pai Cheng , Jilei Hou , and Hadi Esmaeilzadeh . 2020. Ordering chaos: Memory-aware scheduling of irregularly wired neural networks for edge devices. arXiv preprint arXiv:2003.02369 ( 2020 ). Byung\u00a0Hoon Ahn, Jinwon Lee, Jamie\u00a0Menjay Lin, Hsin-Pai Cheng, Jilei Hou, and Hadi Esmaeilzadeh. 2020. Ordering chaos: Memory-aware scheduling of irregularly wired neural networks for edge devices. arXiv preprint arXiv:2003.02369 (2020)."},{"key":"e_1_3_2_1_7_1","volume-title":"Benchmarking TinyML systems: Challenges and direction. arXiv preprint arXiv:2003.04821","author":"Banbury R","year":"2020","unstructured":"Colby\u00a0 R Banbury , Vijay\u00a0Janapa Reddi , Max Lam , William Fu , Amin Fazel , Jeremy Holleman , Xinyuan Huang , Robert Hurtado , David Kanter , Anton Lokhmotov , 2020. Benchmarking TinyML systems: Challenges and direction. arXiv preprint arXiv:2003.04821 ( 2020 ). Colby\u00a0R Banbury, Vijay\u00a0Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, 2020. Benchmarking TinyML systems: Challenges and direction. arXiv preprint arXiv:2003.04821 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_9_1","unstructured":"James Bradbury Roy Frostig Peter Hawkins Matthew\u00a0James Johnson Chris Leary Dougal Maclaurin George Necula Adam Paszke Jake VanderPlas Skye Wanderman-Milne and Qiao Zhang. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax  James Bradbury Roy Frostig Peter Hawkins Matthew\u00a0James Johnson Chris Leary Dougal Maclaurin George Necula Adam Paszke Jake VanderPlas Skye Wanderman-Milne and Qiao Zhang. 2018. JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax"},{"key":"e_1_3_2_1_10_1","volume-title":"Not Trainable Parameters for Efficient On-Device Learning. arXiv preprint arXiv:2007.11622","author":"Cai Han","year":"2020","unstructured":"Han Cai , Chuang Gan , Ligeng Zhu , and Song Han . 2020. TinyTL: Reduce Activations , Not Trainable Parameters for Efficient On-Device Learning. arXiv preprint arXiv:2007.11622 ( 2020 ). Han Cai, Chuang Gan, Ligeng Zhu, and Song Han. 2020. TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning. arXiv preprint arXiv:2007.11622 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Ken Chatfield Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2014. Return of the devil in the details: Delving deep into convolutional nets. In BMVC.  Ken Chatfield Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2014. Return of the devil in the details: Delving deep into convolutional nets. In BMVC.","DOI":"10.5244\/C.28.6"},{"key":"e_1_3_2_1_12_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). 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_13_1","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze 2018. { TVM} : An automated end-to-end optimizing compiler for deep learning. In OSDI.  Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze 2018. { TVM} : An automated end-to-end optimizing compiler for deep learning. In OSDI."},{"key":"e_1_3_2_1_14_1","unstructured":"Xiangning Chen Chen Liang Da Huang Esteban Real Kaiyuan Wang Yao Liu Hieu Pham Xuanyi Dong Thang Luong Cho-Jui Hsieh Yifeng Lu and Quoc\u00a0V. Le. 2023. Symbolic Discovery of Optimization Algorithms. arxiv:2302.06675\u00a0[cs.LG]  Xiangning Chen Chen Liang Da Huang Esteban Real Kaiyuan Wang Yao Liu Hieu Pham Xuanyi Dong Thang Luong Cho-Jui Hsieh Yifeng Lu and Quoc\u00a0V. Le. 2023. Symbolic Discovery of Optimization Algorithms. arxiv:2302.06675\u00a0[cs.LG]"},{"key":"e_1_3_2_1_15_1","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/vicuna.lmsys.org","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang , Zhuohan Li , Zi Lin , Ying Sheng , Zhanghao Wu , Hao Zhang , Lianmin Zheng , Siyuan Zhuang , Yonghao Zhuang , Joseph\u00a0 E. Gonzalez , Ion Stoica , and Eric\u00a0 P. Xing . 2023 . Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/vicuna.lmsys.org Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph\u00a0E. Gonzalez, Ion Stoica, and Eric\u00a0P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/vicuna.lmsys.org"},{"key":"e_1_3_2_1_16_1","volume-title":"Visual wake words dataset. arXiv preprint arXiv:1906.05721","author":"Chowdhery Aakanksha","year":"2019","unstructured":"Aakanksha Chowdhery , Pete Warden , Jonathon Shlens , Andrew Howard , and Rocky Rhodes . 2019. Visual wake words dataset. arXiv preprint arXiv:1906.05721 ( 2019 ). Aakanksha Chowdhery, Pete Warden, Jonathon Shlens, Andrew Howard, and Rocky Rhodes. 2019. Visual wake words dataset. arXiv preprint arXiv:1906.05721 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Jia Deng Wei Dong Richard Socher Li-Jia Li Kai Li and Li Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR.  Jia Deng Wei Dong Richard Socher Li-Jia Li Kai Li and Li Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_18_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). 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_19_1","volume-title":"Decaf: A deep convolutional activation feature for generic visual recognition. In ICML.","author":"Donahue Jeff","year":"2014","unstructured":"Jeff Donahue , Yangqing Jia , Oriol Vinyals , Judy Hoffman , Ning Zhang , Eric Tzeng , and Trevor Darrell . 2014 . Decaf: A deep convolutional activation feature for generic visual recognition. In ICML. Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. 2014. Decaf: A deep convolutional activation feature for generic visual recognition. In ICML."},{"key":"e_1_3_2_1_20_1","volume-title":"Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs. arXiv preprint arXiv:2003.00152","author":"Frankle Jonathan","year":"2020","unstructured":"Jonathan Frankle , David\u00a0 J Schwab , and Ari\u00a0 S Morcos . 2020. Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs. arXiv preprint arXiv:2003.00152 ( 2020 ). Jonathan Frankle, David\u00a0J Schwab, and Ari\u00a0S Morcos. 2020. Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs. arXiv preprint arXiv:2003.00152 (2020)."},{"key":"e_1_3_2_1_21_1","volume-title":"Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR. 2568\u20132577.","author":"Gan Chuang","year":"2015","unstructured":"Chuang Gan , Naiyan Wang , Yi Yang , Dit-Yan Yeung , and Alex\u00a0 G Hauptmann . 2015 . Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR. 2568\u20132577. Chuang Gan, Naiyan Wang, Yi Yang, Dit-Yan Yeung, and Alex\u00a0G Hauptmann. 2015. Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR. 2568\u20132577."},{"key":"e_1_3_2_1_22_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR."},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Machine Learning. PMLR, 2790\u20132799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby , Andrei Giurgiu , Stanislaw Jastrzebski , Bruna Morrone , Quentin De\u00a0Laroussilhe , Andrea Gesmundo , Mona Attariyan , and Sylvain Gelly . 2019 . Parameter-efficient transfer learning for NLP . In International Conference on Machine Learning. PMLR, 2790\u20132799 . Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De\u00a0Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790\u20132799."},{"key":"e_1_3_2_1_24_1","unstructured":"Edward Hu Yelong Shen Phil Wallis Zeyuan Allen-Zhu Yuanzhi Li Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:2106.09685\u00a0[cs.CL]  Edward Hu Yelong Shen Phil Wallis Zeyuan Allen-Zhu Yuanzhi Li Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:2106.09685\u00a0[cs.CL]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342091"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_1_27_1","first-page":"27","article-title":"Optimizing DNN computation with relaxed graph substitutions","volume":"1","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia , James Thomas , Todd Warszawski , Mingyu Gao , Matei Zaharia , and Alex Aiken . 2019 . Optimizing DNN computation with relaxed graph substitutions . Proceedings of Machine Learning and Systems 1 (2019), 27 \u2013 39 . Zhihao Jia, James Thomas, Todd Warszawski, Mingyu Gao, Matei Zaharia, and Alex Aiken. 2019. Optimizing DNN computation with relaxed graph substitutions. Proceedings of Machine Learning and Systems 1 (2019), 27\u201339.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_28_1","first-page":"27","article-title":"Optimizing DNN computation with relaxed graph substitutions","volume":"1","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia , James Thomas , Todd Warszawski , Mingyu Gao , Matei Zaharia , and Alex Aiken . 2019 . Optimizing DNN computation with relaxed graph substitutions . Proceedings of Machine Learning and Systems 1 (2019), 27 \u2013 39 . Zhihao Jia, James Thomas, Todd Warszawski, Mingyu Gao, Matei Zaharia, and Alex Aiken. 2019. Optimizing DNN computation with relaxed graph substitutions. Proceedings of Machine Learning and Systems 1 (2019), 27\u201339.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"MNN: A universal and efficient inference engine. arXiv preprint arXiv:2002.12418","author":"Jiang Xiaotang","year":"2020","unstructured":"Xiaotang Jiang , Huan Wang , Yiliu Chen , Ziqi Wu , Lichuan Wang , Bin Zou , Yafeng Yang , Zongyang Cui , Yu Cai , Tianhang Yu , 2020 . MNN: A universal and efficient inference engine. arXiv preprint arXiv:2002.12418 (2020). Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Bin Zou, Yafeng Yang, Zongyang Cui, Yu Cai, Tianhang Yu, 2020. MNN: A universal and efficient inference engine. arXiv preprint arXiv:2002.12418 (2020)."},{"key":"e_1_3_2_1_30_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0 P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_32_1","unstructured":"Alex Krizhevsky Geoffrey Hinton 2009. Learning multiple layers of features from tiny images. (2009).  Alex Krizhevsky Geoffrey Hinton 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_33_1","volume-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054","author":"Kumar Ananya","year":"2022","unstructured":"Ananya Kumar , Aditi Raghunathan , Robbie Jones , Tengyu Ma , and Percy Liang . 2022. Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054 ( 2022 ). Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, and Percy Liang. 2022. Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054 (2022)."},{"key":"e_1_3_2_1_34_1","volume-title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts. arXiv preprint arXiv:2210.11466","author":"Lee Yoonho","year":"2022","unstructured":"Yoonho Lee , Annie\u00a0 S Chen , Fahim Tajwar , Ananya Kumar , Huaxiu Yao , Percy Liang , and Chelsea Finn . 2022. Surgical Fine-Tuning Improves Adaptation to Distribution Shifts. arXiv preprint arXiv:2210.11466 ( 2022 ). Yoonho Lee, Annie\u00a0S Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, and Chelsea Finn. 2022. Surgical Fine-Tuning Improves Adaptation to Distribution Shifts. arXiv preprint arXiv:2210.11466 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. of the 1st USENIX\/ACM Symp. on Networked Systems Design and Implementation, Vol.\u00a025","author":"Levis Philip","year":"2004","unstructured":"Philip Levis , Neil Patel , David Culler , and Scott Shenker . 2004 . Trickle: A self-regulating algorithm for code propagation and maintenance in wireless sensor networks . In Proc. of the 1st USENIX\/ACM Symp. on Networked Systems Design and Implementation, Vol.\u00a025 . 37\u201352. Philip Levis, Neil Patel, David Culler, and Scott Shenker. 2004. Trickle: A self-regulating algorithm for code propagation and maintenance in wireless sensor networks. In Proc. of the 1st USENIX\/ACM Symp. on Networked Systems Design and Implementation, Vol.\u00a025. 37\u201352."},{"key":"e_1_3_2_1_36_1","unstructured":"Xuechen Li Tianyi Zhang Yann Dubois Rohan Taori Ishaan Gulrajani Carlos Guestrin Percy Liang and Tatsunori\u00a0B. Hashimoto. 2023. AlpacaEval: An Automatic Evaluator of Instruction-following Models. https:\/\/github.com\/tatsu-lab\/alpaca_eval.  Xuechen Li Tianyi Zhang Yann Dubois Rohan Taori Ishaan Gulrajani Carlos Guestrin Percy Liang and Tatsunori\u00a0B. Hashimoto. 2023. AlpacaEval: An Automatic Evaluator of Instruction-following Models. https:\/\/github.com\/tatsu-lab\/alpaca_eval."},{"key":"e_1_3_2_1_37_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang\u00a0Lisa","year":"2021","unstructured":"Xiang\u00a0Lisa Li and Percy Liang . 2021 . Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021). Xiang\u00a0Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_38_1","volume-title":"Neural networks on microcontrollers: saving memory at inference via operator reordering. arXiv preprint arXiv:1910.05110","author":"Liberis Edgar","year":"2019","unstructured":"Edgar Liberis and Nicholas\u00a0 D Lane . 2019. Neural networks on microcontrollers: saving memory at inference via operator reordering. arXiv preprint arXiv:1910.05110 ( 2019 ). Edgar Liberis and Nicholas\u00a0D Lane. 2019. Neural networks on microcontrollers: saving memory at inference via operator reordering. arXiv preprint arXiv:1910.05110 (2019)."},{"key":"e_1_3_2_1_39_1","volume-title":"Mcunetv2: Memory-efficient patch-based inference for tiny deep learning. arXiv preprint arXiv:2110.15352","author":"Lin Ji","year":"2021","unstructured":"Ji Lin , Wei-Ming Chen , Han Cai , Chuang Gan , and Song Han . 2021. Mcunetv2: Memory-efficient patch-based inference for tiny deep learning. arXiv preprint arXiv:2110.15352 ( 2021 ). Ji Lin, Wei-Ming Chen, Han Cai, Chuang Gan, and Song Han. 2021. Mcunetv2: Memory-efficient patch-based inference for tiny deep learning. arXiv preprint arXiv:2110.15352 (2021)."},{"key":"e_1_3_2_1_40_1","volume-title":"Mcunet: Tiny deep learning on iot devices. In NeurIPS.","author":"Lin Ji","year":"2020","unstructured":"Ji Lin , Wei-Ming Chen , Yujun Lin , John Cohn , Chuang Gan , and Song Han . 2020 . Mcunet: Tiny deep learning on iot devices. In NeurIPS. Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, and Song Han. 2020. Mcunet: Tiny deep learning on iot devices. In NeurIPS."},{"key":"e_1_3_2_1_41_1","unstructured":"Ji Lin Ligeng Zhu Wei-Ming Chen Wei-Chen Wang Chuang Gan and Song Han. 2022. On-Device Training Under 256KB Memory. In NeurIPS.  Ji Lin Ligeng Zhu Wei-Ming Chen Wei-Chen Wang Chuang Gan and Song Han. 2022. On-Device Training Under 256KB Memory. In NeurIPS."},{"key":"e_1_3_2_1_42_1","volume-title":"K for the price of 1: Parameter-efficient multi-task and transfer learning. arXiv preprint arXiv:1810.10703","author":"Mudrakarta Pramod\u00a0Kaushik","year":"2018","unstructured":"Pramod\u00a0Kaushik Mudrakarta , Mark Sandler , Andrey Zhmoginov , and Andrew Howard . 2018. K for the price of 1: Parameter-efficient multi-task and transfer learning. arXiv preprint arXiv:1810.10703 ( 2018 ). Pramod\u00a0Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, and Andrew Howard. 2018. K for the price of 1: Parameter-efficient multi-task and transfer learning. arXiv preprint arXiv:1810.10703 (2018)."},{"key":"e_1_3_2_1_43_1","unstructured":"Pramod\u00a0Kaushik Mudrakarta Mark Sandler Andrey Zhmoginov and Andrew Howard. 2019. K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning. In ICLR.  Pramod\u00a0Kaushik Mudrakarta Mark Sandler Andrey Zhmoginov and Andrew Howard. 2019. K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning. In ICLR."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_1_46_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 , 2019 . Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019). Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_47_1","volume-title":"POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging. In International Conference on Machine Learning. PMLR, 17573\u201317583","author":"Patil G","year":"2022","unstructured":"Shishir\u00a0 G Patil , Paras Jain , Prabal Dutta , Ion Stoica , and Joseph Gonzalez . 2022 . POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging. In International Conference on Machine Learning. PMLR, 17573\u201317583 . Shishir\u00a0G Patil, Paras Jain, Prabal Dutta, Ion Stoica, and Joseph Gonzalez. 2022. POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging. In International Conference on Machine Learning. PMLR, 17573\u201317583."},{"key":"e_1_3_2_1_48_1","unstructured":"Qualcomm. [n. d.]. Snapdragon Neural Processing Engine SDK. https:\/\/developer.qualcomm.com\/sites\/default\/files\/docs\/snpe\/overview.html.  Qualcomm. [n. d.]. Snapdragon Neural Processing Engine SDK. https:\/\/developer.qualcomm.com\/sites\/default\/files\/docs\/snpe\/overview.html."},{"key":"e_1_3_2_1_49_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever 2018. Improving language understanding by generative pre-training. (2018).  Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang-Chieh Chen. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In CVPR.  Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang-Chieh Chen. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In CVPR.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_51_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh , Lysandre Debut , Julien Chaumond , and Thomas Wolf . 2019. DistilBERT , a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 ( 2019 ). Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_52_1","volume-title":"CVPR Workshops.","author":"Sharif\u00a0Razavian Ali","year":"2014","unstructured":"Ali Sharif\u00a0Razavian , Hossein Azizpour , Josephine Sullivan , and Stefan Carlsson . 2014 . CNN features off-the-shelf: an astounding baseline for recognition . In CVPR Workshops. Ali Sharif\u00a0Razavian, Hossein Azizpour, Josephine Sullivan, and Stefan Carlsson. 2014. CNN features off-the-shelf: an astounding baseline for recognition. In CVPR Workshops."},{"key":"e_1_3_2_1_53_1","volume-title":"International conference on machine learning. PMLR, 9229\u20139248","author":"Sun Yu","year":"2020","unstructured":"Yu Sun , Xiaolong Wang , Zhuang Liu , John Miller , Alexei Efros , and Moritz Hardt . 2020 . Test-time training with self-supervision for generalization under distribution shifts . In International conference on machine learning. PMLR, 9229\u20139248 . Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei Efros, and Moritz Hardt. 2020. Test-time training with self-supervision for generalization under distribution shifts. In International conference on machine learning. PMLR, 9229\u20139248."},{"key":"e_1_3_2_1_54_1","volume-title":"Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca.","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori , Ishaan Gulrajani , Tianyi Zhang , Yann Dubois , Xuechen Li , Carlos Guestrin , Percy Liang , and Tatsunori\u00a0 B. Hashimoto . 2023 . Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori\u00a0B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_55_1","volume-title":"Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron , Louis Martin , Kevin Stone , Peter Albert , Amjad Almahairi , Yasmine Babaei , Nikolay Bashlykov , Soumya Batra , Prajjwal Bhargava , Shruti Bhosale , 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 ( 2023 ). Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Vasisht Deepak","year":"2017","unstructured":"Deepak Vasisht , Zerina Kapetanovic , Jongho Won , Xinxin Jin , Ranveer Chandra , Sudipta Sinha , Ashish Kapoor , Madhusudhan Sudarshan , and Sean Stratman . 2017 . { FarmBeats} : An { IoT} Platform for { Data-Driven} Agriculture . In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17) . 515\u2013529. Deepak Vasisht, Zerina Kapetanovic, Jongho Won, Xinxin Jin, Ranveer Chandra, Sudipta Sinha, Ashish Kapoor, Madhusudhan Sudarshan, and Sean Stratman. 2017. { FarmBeats} : An { IoT} Platform for { Data-Driven} Agriculture. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 515\u2013529."},{"key":"e_1_3_2_1_57_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan\u00a0 N Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)."},{"key":"e_1_3_2_1_58_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang , Amanpreet Singh , Julian Michael , Felix Hill , Omer Levy , and Samuel\u00a0 R Bowman . 2018 . GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018). Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel\u00a0R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Yizhong Wang Yeganeh Kordi Swaroop Mishra Alisa Liu Noah\u00a0A. Smith Daniel Khashabi and Hannaneh Hajishirzi. 2022. Self-Instruct: Aligning Language Model with Self Generated Instructions. arxiv:2212.10560\u00a0[cs.CL]  Yizhong Wang Yeganeh Kordi Swaroop Mishra Alisa Liu Noah\u00a0A. Smith Daniel Khashabi and Hannaneh Hajishirzi. 2022. Self-Instruct: Aligning Language Model with Self Generated Instructions. arxiv:2212.10560\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"e_1_3_2_1_60_1","unstructured":"Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD Birds 200. Technical Report CNS-TR-201. Caltech. \/se3\/wp-content\/uploads\/2014\/09\/WelinderEtal10_CUB-200.pdf http:\/\/www.vision.caltech.edu\/visipedia\/CUB-200.html  Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD Birds 200. Technical Report CNS-TR-201. Caltech. \/se3\/wp-content\/uploads\/2014\/09\/WelinderEtal10_CUB-200.pdf http:\/\/www.vision.caltech.edu\/visipedia\/CUB-200.html"},{"key":"e_1_3_2_1_61_1","volume-title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models. CoRR abs\/2106.10199","author":"Zaken Elad\u00a0Ben","year":"2021","unstructured":"Elad\u00a0Ben Zaken , Shauli Ravfogel , and Yoav Goldberg . 2021. BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models. CoRR abs\/2106.10199 ( 2021 ). arXiv:2106.10199https:\/\/arxiv.org\/abs\/2106.10199 Elad\u00a0Ben Zaken, Shauli Ravfogel, and Yoav Goldberg. 2021. BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models. CoRR abs\/2106.10199 (2021). arXiv:2106.10199https:\/\/arxiv.org\/abs\/2106.10199"},{"key":"e_1_3_2_1_62_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric.\u00a0P Xing Hao Zhang Joseph\u00a0E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arxiv:2306.05685\u00a0[cs.CL]  Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric.\u00a0P Xing Hao Zhang Joseph\u00a0E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arxiv:2306.05685\u00a0[cs.CL]"},{"key":"e_1_3_2_1_63_1","volume-title":"LIMA: Less Is More for Alignment. arxiv:2305.11206\u00a0[cs.CL]","author":"Zhou Chunting","year":"2023","unstructured":"Chunting Zhou , Pengfei Liu , Puxin Xu , Srini Iyer , Jiao Sun , Yuning Mao , Xuezhe Ma , Avia Efrat , Ping Yu , Lili Yu , Susan Zhang , Gargi Ghosh , Mike Lewis , Luke Zettlemoyer , and Omer Levy . 2023 . LIMA: Less Is More for Alignment. arxiv:2305.11206\u00a0[cs.CL] Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. 2023. LIMA: Less Is More for Alignment. arxiv:2305.11206\u00a0[cs.CL]"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"MICRO '23: 56th Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Toronto ON Canada","acronym":"MICRO '23","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["56th Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614307","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613424.3614307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:30Z","timestamp":1750178190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":65,"alternative-id":["10.1145\/3613424.3614307","10.1145\/3613424"],"URL":"https:\/\/doi.org\/10.1145\/3613424.3614307","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]},"assertion":[{"value":"2023-12-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}