cs249r_book/contents/optimizations/optimizations.bib

@inproceedings{benmeziane2021hardwareaware,
 author = {Benmeziane, Hadjer and El Maghraoui, Kaoutar and Ouarnoughi, Hamza and Niar, Smail and Wistuba, Martin and Wang, Naigang},
 bdsk-url-1 = {https://doi.org/10.24963/ijcai.2021/592},
 booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence},
 doi = {10.24963/ijcai.2021/592},
 editor = {Zhou, Zhi-Hua},
 note = {Survey Track},
 pages = {4322--4329},
 publisher = {International Joint Conferences on Artificial Intelligence Organization},
 source = {Crossref},
 title = {Hardware-Aware Neural Architecture Search: {Survey} and Taxonomy},
 url = {https://doi.org/10.24963/ijcai.2021/592},
 year = {2021}
}

@inproceedings{cai2018proxylessnas,
 author = {Han Cai and Ligeng Zhu and Song Han},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/iclr/CaiZH19.bib},
 booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019},
 publisher = {OpenReview.net},
 timestamp = {Tue, 24 Nov 2020 00:00:00 +0100},
 title = {ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware},
 url = {https://openreview.net/forum?id=HylVB3AqYm},
 year = {2019}
}

@inproceedings{chu2021discovering,
 author = {Grace Chu and Okan Arikan and Gabriel Bender and Weijun Wang and Achille Brighton and Pieter{-}Jan Kindermans and Hanxiao Liu and Berkin Akin and Suyog Gupta and Andrew Howard},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/cvpr/ChuABWBKLAG021.bib},
 booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition Workshops, {CVPR} Workshops 2021, virtual, June 19-25, 2021},
 doi = {10.1109/CVPRW53098.2021.00337},
 pages = {3022--3031},
 publisher = {Computer Vision Foundation / {IEEE}},
 timestamp = {Mon, 18 Jul 2022 01:00:00 +0200},
 title = {Discovering Multi-Hardware Mobile Models via Architecture Search},
 url = {https://openaccess.thecvf.com/content/CVPR2021W/ECV/html/Chu\_Discovering\_Multi-Hardware\_Mobile\_Models\_via\_Architecture\_Search\_CVPRW\_2021\_paper.html},
 year = {2021}
}

@inproceedings{dong2022splitnets,
 author = {Xin Dong and Barbara De Salvo and Meng Li and Chiao Liu and Zhongnan Qu and H. T. Kung and Ziyun Li},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/cvpr/DongSLLQ0L22.bib},
 booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022},
 doi = {10.1109/CVPR52688.2022.01223},
 pages = {12549--12559},
 publisher = {{IEEE}},
 timestamp = {Sun, 22 Jan 2023 00:00:00 +0100},
 title = {SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems},
 url = {https://doi.org/10.1109/CVPR52688.2022.01223},
 year = {2022}
}

@misc{fahim2021hls4ml,
 archiveprefix = {arXiv},
 author = {Fahim, Farah and Hawks, Benjamin and Herwig, Christian and Hirschauer, James and Jindariani, Sergo and Tran, Nhan and Carloni, Luca P. and Guglielmo, Giuseppe Di and Harris, Philip and Krupa, Jeffrey and Rankin, Dylan and Valentin, Manuel Blanco and Hester, Josiah and Luo, Yingyi and Mamish, John and Orgrenci-Memik, Seda and Aarrestad, Thea and Javed, Hamza and Loncar, Vladimir and Pierini, Maurizio and Pol, Adrian Alan and Summers, Sioni and Duarte, Javier and Hauck, Scott and Hsu, Shih-Chieh and Ngadiuba, Jennifer and Liu, Mia and Hoang, Duc and Kreinar, Edward and Wu, Zhenbin},
 eprint = {2103.05579},
 primaryclass = {cs.LG},
 title = {hls4ml: {An} Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices},
 year = {2021}
}

@misc{gholami2021survey,
 author = {Gholami and Kim, Dong and Yao, Mahoney and Keutzer},
 journal = {ArXiv preprint},
 title = {A Survey of Quantization Methods for Efficient Neural Network Inference)},
 url = {https://arxiv.org/abs/2103.13630},
 volume = {abs/2103.13630},
 year = {2021}
}

@misc{google2023three,
 author = {Google},
 bdsk-url-1 = {https://storage.googleapis.com/gweb-cloudblog-publish/images/Three\_floating-point\_formats.max-624x261.png},
 title = {Three Floating Point Formats},
 url = {https://storage.googleapis.com/gweb-cloudblog-publish/images/Three\_floating-point\_formats.max-624x261.png},
 urldate = {2023-10-20},
 year = {2023}
}

@inproceedings{gordon2018morphnet,
 author = {Gordon, Ariel and Eban, Elad and Nachum, Ofir and Chen, Bo and Wu, Hao and Yang, Tien-Ju and Choi, Edward},
 booktitle = {2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
 doi = {10.1109/cvpr.2018.00171},
 pages = {1586--1595},
 publisher = {IEEE},
 source = {Crossref},
 title = {{MorphNet:} {Fast} \& Simple Resource-Constrained Structure Learning of Deep Networks},
 url = {https://doi.org/10.1109/cvpr.2018.00171},
 year = {2018}
}

@misc{gu2023deep,
 author = {Gu, Ivy},
 bdsk-url-1 = {https://ivygdy.medium.com/deep-learning-model-compression-ii-546352ea9453},
 title = {Deep Learning Model Compression (ii) by Ivy Gu Medium},
 url = {https://ivygdy.medium.com/deep-learning-model-compression-ii-546352ea9453},
 urldate = {2023-10-20},
 year = {2023}
}

@misc{han2015deep,
 author = {Han and Mao and Dally},
 journal = {ArXiv preprint},
 title = {Deep Compression: {Compressing} Deep Neural Networks with Pruning, Trained Quantization and {Huffman} Coding},
 url = {https://arxiv.org/abs/1510.00149},
 volume = {abs/1510.00149},
 year = {2015}
}

@misc{hegde2023introduction,
 author = {Hegde, Sumant},
 bdsk-url-1 = {https://www.analyticsvidhya.com/blog/2021/11/an-introduction-to-separable-convolutions/},
 title = {An Introduction to Separable Convolutions - Analytics Vidhya},
 url = {https://www.analyticsvidhya.com/blog/2021/11/an-introduction-to-separable-convolutions/},
 urldate = {2023-10-20},
 year = {2023}
}

@misc{hinton2015distilling,
 archiveprefix = {arXiv},
 author = {Hinton, Geoffrey},
 doi = {10.1002/0471743984.vse0673},
 eprint = {1503.02531},
 isbn = {9780471332305, 9780471743989},
 primaryclass = {stat.ML},
 publisher = {Wiley},
 source = {Crossref},
 title = {Van {Nostrand's} Scientific Encyclopedia},
 url = {https://doi.org/10.1002/0471743984.vse0673},
 year = {2005}
}

@misc{howard2017mobilenets,
 author = {Howard, Andrew G. and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig},
 journal = {ArXiv preprint},
 title = {{MobileNets:} {Efficient} Convolutional Neural Networks for Mobile Vision Applications},
 url = {https://arxiv.org/abs/1704.04861},
 volume = {abs/1704.04861},
 year = {2017}
}

@article{iandola2016squeezenet,
 author = {Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},
 journal = {ArXiv preprint},
 title = {{SqueezeNet:} {Alexnet-level} accuracy with 50x fewer parameters and 0.5 {MB} model size},
 url = {https://arxiv.org/abs/1602.07360},
 volume = {abs/1602.07360},
 year = {2016}
}

@misc{intellabs2023knowledge,
 author = {IntelLabs},
 bdsk-url-1 = {https://intellabs.github.io/distiller/knowledge_distillation.html},
 title = {Knowledge Distillation - Neural Network Distiller},
 url = {https://intellabs.github.io/distiller/knowledge_distillation.html},
 urldate = {2023-10-20},
 year = {2023}
}

@misc{isscc2014computings,
 author = {Isscc},
 bdsk-url-1 = {https://ieeexplore.ieee.org/document/6757323},
 title = {Computing's energy problem (and what we can do about it)},
 url = {https://ieeexplore.ieee.org/document/6757323},
 urldate = {2014-03-06},
 year = {2014}
}

@misc{jiang2019accuracy,
 archiveprefix = {arXiv},
 author = {Jiang, Weiwen and Zhang, Xinyi and Sha, Edwin H. -M. and Yang, Lei and Zhuge, Qingfeng and Shi, Yiyu and Hu, Jingtong},
 eprint = {1901.11211},
 primaryclass = {cs.DC},
 title = {Accuracy vs. Efficiency: {Achieving} Both through {FPGA}-Implementation Aware Neural Architecture Search},
 year = {2019}
}

@inproceedings{jonathan2019lottery,
 author = {Jonathan Frankle and Michael Carbin},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/iclr/FrankleC19.bib},
 booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019},
 publisher = {OpenReview.net},
 timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
 title = {The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks},
 url = {https://openreview.net/forum?id=rJl-b3RcF7},
 year = {2019}
}

@article{koren2009matrix,
 author = {Koren, Yehuda and Bell, Robert and Volinsky, Chris},
 journal = {Computer},
 number = {8},
 pages = {30--37},
 publisher = {IEEE},
 title = {Matrix factorization techniques for recommender systems},
 volume = {42},
 year = {2009}
}

@misc{krishna2023raman,
 archiveprefix = {arXiv},
 author = {Krishna, Adithya and Nudurupati, Srikanth Rohit and G, Chandana D and Dwivedi, Pritesh and van Schaik, Andr\'e and Mehendale, Mahesh and Thakur, Chetan Singh},
 eprint = {2306.06493},
 primaryclass = {cs.NE},
 title = {{RAMAN:} {A} Re-configurable and Sparse {TinyML} Accelerator for Inference on Edge},
 year = {2023}
}

@misc{krishnamoorthi2018quantizing,
 author = {Krishnamoorthi},
 journal = {ArXiv preprint},
 title = {Quantizing deep convolutional networks for efficient inference: {A} whitepaper},
 url = {https://arxiv.org/abs/1806.08342},
 volume = {abs/1806.08342},
 year = {2018}
}

@misc{kung2018packing,
 archiveprefix = {arXiv},
 author = {Kung, H. T. and McDanel, Bradley and Zhang, Sai Qian},
 eprint = {1811.04770},
 primaryclass = {cs.LG},
 title = {Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: {Column} Combining Under Joint Optimization},
 year = {2018}
}

@misc{kuzmin2022fp8,
 archiveprefix = {arXiv},
 author = {Kuzmin, Andrey and Baalen, Mart Van and Ren, Yuwei and Nagel, Markus and Peters, Jorn and Blankevoort, Tijmen},
 eprint = {2208.09225},
 primaryclass = {cs.LG},
 title = {{FP8} Quantization: {The} Power of the Exponent},
 year = {2022}
}

@article{kwon2021hardwaresoftware,
 article-number = {11073},
 author = {Kwon, Jisu and Park, Daejin},
 bdsk-url-1 = {https://www.mdpi.com/2076-3417/11/22/11073},
 bdsk-url-2 = {https://doi.org/10.3390/app112211073},
 doi = {10.3390/app112211073},
 issn = {2076-3417},
 journal = {Applied Sciences},
 number = {22},
 pages = {11073},
 publisher = {MDPI AG},
 source = {Crossref},
 title = {{Hardware/Software} Co-Design for {TinyML} Voice-Recognition Application on Resource Frugal Edge Devices},
 url = {https://doi.org/10.3390/app112211073},
 volume = {11},
 year = {2021}
}

@misc{lai2018cmsisnn,
 archiveprefix = {arXiv},
 author = {Lai, Liangzhen and Suda, Naveen and Chandra, Vikas},
 eprint = {1801.06601},
 primaryclass = {cs.NE},
 title = {{CMSIS}-{NN:} {Efficient} Neural Network Kernels for Arm Cortex-M {CPUs}},
 year = {2018}
}

@inproceedings{lin2020mcunet,
 author = {Ji Lin and Wei{-}Ming Chen and Yujun Lin and John Cohn and Chuang Gan and Song Han},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/nips/LinCLCG020.bib},
 booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual},
 editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin},
 timestamp = {Thu, 11 Feb 2021 00:00:00 +0100},
 title = {MCUNet: Tiny Deep Learning on IoT Devices},
 url = {https://proceedings.neurips.cc/paper/2020/hash/86c51678350f656dcc7f490a43946ee5-Abstract.html},
 year = {2020}
}

@misc{lin2023awq,
 author = {Lin and Tang, Tang and Yang, Dang and Gan, Han},
 journal = {ArXiv preprint},
 title = {{AWQ:} {Activation-aware} Weight Quantization for {LLM} Compression and Acceleration},
 url = {https://arxiv.org/abs/2306.00978},
 volume = {abs/2306.00978},
 year = {2023}
}

@inproceedings{prakash2022cfu,
 author = {Prakash, Shvetank and Callahan, Tim and Bushagour, Joseph and Banbury, Colby and Green, Alan V. and Warden, Pete and Ansell, Tim and Reddi, Vijay Janapa},
 journal = {ArXiv preprint},
 title = {{CFU} Playground: {Full-stack} Open-Source Framework for Tiny Machine Learning {(TinyML)} Acceleration on {FPGAs}},
 url = {https://arxiv.org/abs/2201.01863},
 volume = {abs/2201.01863},
 year = {2022}
}

@article{qi2021efficient,
 abstract = {Nowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2\% and 94.1\%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.},
 author = {Qi, Chen and Shen, Shibo and Li, Rongpeng and Zhao, Zhifeng and Liu, Qing and Liang, Jing and Zhang, Honggang},
 bdsk-url-1 = {https://doi.org/10.1186/s13634-021-00744-4},
 doi = {10.1186/s13634-021-00744-4},
 file = {Full Text PDF:/Users/jeffreyma/Zotero/storage/AGWCC5VS/Qi et al. - 2021 - An efficient pruning scheme of deep neural network.pdf:application/pdf},
 issn = {1687-6180},
 journal = {EURASIP Journal on Advances in Signal Processing},
 number = {1},
 publisher = {Springer Science and Business Media LLC},
 source = {Crossref},
 title = {An efficient pruning scheme of deep neural networks for Internet of Things applications},
 url = {https://doi.org/10.1186/s13634-021-00744-4},
 volume = {2021},
 year = {2021}
}

@article{sheng2019qbert,
 author = {Sheng Shen and
Zhen Dong and
Jiayu Ye and
Linjian Ma and
Zhewei Yao and
Amir Gholami and
Michael W. Mahoney and
Kurt Keutzer},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/journals/corr/abs-1909-05840.bib},
 eprint = {1909.05840},
 eprinttype = {arXiv},
 journal = {CoRR},
 timestamp = {Wed, 18 Sep 2019 10:38:36 +0200},
 title = {{Q-BERT:} Hessian Based Ultra Low Precision Quantization of {BERT}},
 url = {http://arxiv.org/abs/1909.05840},
 volume = {abs/1909.05840},
 year = {2019}
}

@inproceedings{tan2019mnasnet,
 author = {Mingxing Tan and Bo Chen and Ruoming Pang and Vijay Vasudevan and Mark Sandler and Andrew Howard and Quoc V. Le},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/cvpr/TanCPVSHL19.bib},
 booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019},
 doi = {10.1109/CVPR.2019.00293},
 pages = {2820--2828},
 publisher = {Computer Vision Foundation / {IEEE}},
 timestamp = {Tue, 12 Jan 2021 00:00:00 +0100},
 title = {MnasNet: Platform-Aware Neural Architecture Search for Mobile},
 url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Tan\_MnasNet\_Platform-Aware\_Neural\_Architecture\_Search\_for\_Mobile\_CVPR\_2019\_paper.html},
 year = {2019}
}

@misc{tan2020efficientnet,
 archiveprefix = {arXiv},
 author = {Tan, Mingxing and Le, Quoc V.},
 doi = {10.1002/9781394205639.ch6},
 eprint = {1905.11946},
 isbn = {9781394205608, 9781394205639},
 pages = {111--131},
 primaryclass = {cs.LG},
 publisher = {Wiley},
 source = {Crossref},
 title = {Demystifying Deep Learning},
 url = {https://doi.org/10.1002/9781394205639.ch6},
 year = {2023}
}

@misc{ultimate,
 bdsk-url-1 = {https://deci.ai/quantization-and-quantization-aware-training/},
 title = {The Ultimate Guide to Deep Learning Model Quantization and Quantization-Aware Training},
 url = {https://deci.ai/quantization-and-quantization-aware-training/}
}

@misc{vaswani2023attention,
 archiveprefix = {arXiv},
 author = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
 eprint = {1706.03762},
 primaryclass = {cs.CL},
 title = {Attention Is All You Need},
 year = {2023}
}

@inproceedings{wu2019fbnet,
 author = {Bichen Wu and Xiaoliang Dai and Peizhao Zhang and Yanghan Wang and Fei Sun and Yiming Wu and Yuandong Tian and Peter Vajda and Yangqing Jia and Kurt Keutzer},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/cvpr/WuDZWSWTVJK19.bib},
 booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019},
 doi = {10.1109/CVPR.2019.01099},
 pages = {10734--10742},
 publisher = {Computer Vision Foundation / {IEEE}},
 timestamp = {Mon, 20 Jan 2020 00:00:00 +0100},
 title = {FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search},
 url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Wu\_FBNet\_Hardware-Aware\_Efficient\_ConvNet\_Design\_via\_Differentiable\_Neural\_Architecture\_Search\_CVPR\_2019\_paper.html},
 year = {2019}
}

@misc{wu2020integer,
 author = {Wu and Judd, Zhang and Isaev, Micikevicius},
 journal = {ArXiv preprint},
 title = {Integer Quantization for Deep Learning Inference: {Principles} and Empirical Evaluation)},
 url = {https://arxiv.org/abs/2004.09602},
 volume = {abs/2004.09602},
 year = {2020}
}

@misc{xiao2022smoothquant,
 author = {Xiao and Lin, Seznec and Wu, Demouth and Han},
 journal = {ArXiv preprint},
 title = {{SmoothQuant:} {Accurate} and Efficient Post-Training Quantization for Large Language Models},
 url = {https://arxiv.org/abs/2211.10438},
 volume = {abs/2211.10438},
 year = {2022}
}

@misc{xinyu,
 abstract = {Some simple examples for showing how to use tensor decomposition to reconstruct fluid dynamics},
 author = {Xinyu, Chen},
 bdsk-url-1 = {https://medium.com/}
}

@inproceedings{xu2018alternating,
 author = {Chen Xu and Jianqiang Yao and Zhouchen Lin and Wenwu Ou and Yuanbin Cao and Zhirong Wang and Hongbin Zha},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/iclr/XuYLOCWZ18.bib},
 booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
 publisher = {OpenReview.net},
 timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
 title = {Alternating Multi-bit Quantization for Recurrent Neural Networks},
 url = {https://openreview.net/forum?id=S19dR9x0b},
 year = {2018}
}

@misc{yang2020coexploration,
 archiveprefix = {arXiv},
 author = {Ho Yoon, Jung and Jung, Hyung-Suk and Hwan Lee, Min and Hwan Kim, Gun and Ji Song, Seul and Yeong Seok, Jun and Jean Yoon, Kyung and Seong Hwang, Cheol and Besland, M.-P. and Tranchant, J. and Souchier, E. and Moreau, P. and Salmon, S. and Corraze, B. and Janod, E. and Cario, L. and Zazpe, Ra\'ul and Ungureanu, Mariana and Llopis, Roger and Golmar, Federico and Stoliar, Pablo and Casanova, F\'elix and Eduardo Hueso, Luis and Hermes, C. and Wimmer, M. and Menzel, S. and Fleck, K. and Rana, V. and Salinga, M. and B\"ottger, U. and Bruchhaus, R. and Wuttig, M. and Waser, R. and Lentz, F. and Hermes, C. and R\"osgen, B. and Selle, T. and Bruchhaus, R. and Rana, V. and Waser, R. and Marchewka, Astrid and Menzel, Stephan and B\"ottger, Ulrich and Waser, Rainer and Hoskins, Brian and Alibart, Fabien and Strukov, Dmitri and Pellegrino, Luca and Manca, Nicola and Kanki, Teruo and Tanaka, Hidekazu and Biasotti, Michele and Bellingeri, Emilio and Sergio Siri, Antonio and Marr\'e, Daniele and M. Padilha, Antonio Claudio and Martini Dalpian, Gustavo and Reily Rocha, Alexandre and Prodromakis, Themistoklis and Salaoru, Iulia and Khiat, Ali and Toumazou, Christopher and Gale, Ella M. and Madhavan, A. and Adam, G. and Alibart, F. and Gao, L. and Strukov, D. B. and Wamwangi, D. and Welnic, W. and Wuttig, M. and Gholipour, Behrad and Huang, Chung-Che and Anastasopoulos, Alexandros and Al-Saab, Feras and Hayden, Brian E. and Hewak, Daniel W. and Lan, Rui and Endo, Rie and Kuwahara, Masashi and Kobayashi, Yoshinao and Susa, Masahiro and Baumeister, Paul and Wortmann, Daniel and Bl\"ugel, Stefan and Mazzarello, Riccardo and Li, Yan and Zhang, Wei and Ronneberger, Ider and Simon, Ronnie and Gallus, Jens and Bessas, Dimitrios and Sergueev, Ilya and Wille, Hans-Christian and Pierre Hermann, Rapha\"el and Luckas, Jennifer and Rausch, Pascal and Krebs, Daniel and Zalden, Peter and Boltz, Janika and Raty, Jean-Yves and Salinga, Martin and Longeaud, Christophe and Wuttig, Matthias and Kim, Haeri and Kim, Dong-Wook and Phark, Soo-Hyon and Hong, Seungbum and Park, C. and Herpers, A. and Bruchhaus, R. and Verbeeck, J. and Egoavil, R. and Borgatti, F. and Panaccione, G. and Offi, F. and Dittmann, R. and Clima, Sergiu and Sankaran, Kiroubanand and Mees, Maarten and Yin Chen, Yang and Goux, Ludovic and Govoreanu, Bogdan and Wouters, Dirk J. and Kittl, Jorge and Jurczak, Malgorzata and Pourtois, Geoffrey and Calka, P. and Martinez, E. and Delaye, V. and Lafond, D. and Audoit, G. and Mariolle, D. and Chevalier, N. and Grampeix, H. and Cagli, C. and Jousseaume, V. and Guedj, C. and Shrestha, Pragya and Ochia, Adaku and Cheung, Kin. P. and Campbell, Jason and Baumgart, Helmut and Harris, Gary and Scherff, Malte and Meyer, Bjoern and Scholz, Julius and Hoffmann, Joerg and Jooss, Christian and Xiao, Bo and Tada, Tomofumi and Gu, Tingkun and Tawara, Arihiro and Watanabe, Satoshi and Young, Tai-Fa and Yang, Ya-Liang and Chang, Ting-Chang and Hsu, Kuang-Ting and Chen, Chao-Yu and Burkert, A and Valov, I. and Staikov, G. and Waser, R. and van den Hurk, Jan and Valov, Ilia and Waser, Rainer and Valov, Ilia and Tappertzhofen, Stefan and van der Hurk, Jan and Waser, Rainer and Adam, G. and Alibart, F. and Gao, L. and Hoskins, B. and Strukov, D. B. and Jean Yoon, Kyung and Ji Song, Seul and Kim, Gun Hwan and Seok, Jun Yeong and Ho Yoon, Jeong and Seong Hwang, Cheol and Yoon, Jung Ho and Yoon, Kyung Jin and Shuai, Yao and Wu, Chuangui and Zhang, Wanli and Zhou, Shengqiang and B\"urger, Danilo and Slesazeck, Stefan and Mikolajick, Thomas and Helm, Manfred and Schmidt, Heidemarie and Gale, Ella and Pearson, David and Kitson, Stephen and Adamatzky, Andrew and Costello, Ben de Lacy and Lehtonen, Eero and Poikonen, Jussi and Laiho, Mika and Kanerva, Pentti and Lim, Hyungkwang and Jang, Ho-won and Jeong, Doo Seok and Cao, Xun and Jiang, Meng and Zhang, Feng and Liu, Xinjun and Jin, Ping and Zhang, Kai and Tangirala, Madhavi and Shrestha, Pragya and Baumgart, Helmut and Kittiwatanakul, Salinporn and Lu, Jiwei and Wolf, Stuart and Pallem, Venkateswara and Dussarrat, Christian and Pinto, S. and Krishna, R. and Dias, C. and Pimentel, G. and Oliveira, G. N. P. and Teixeira, J. M. and Aguiar, P. and Titus, E. and Gracio, J. and Ventura, J. and Araujo, J. P.},
 doi = {10.1002/9783527667703.ch67},
 eprint = {2002.04116},
 isbn = {9783527411917, 9783527667703},
 pages = {523--587},
 primaryclass = {cs.LG},
 publisher = {Wiley},
 source = {Crossref},
 title = {Frontiers in Electronic Materials},
 url = {https://doi.org/10.1002/9783527667703.ch67},
 year = {2012}
}

@inproceedings{zhang2019autoshrink,
 author = {Tunhou Zhang and Hsin{-}Pai Cheng and Zhenwen Li and Feng Yan and Chengyu Huang and Hai Helen Li and Yiran Chen},
 bibsource = {dblp computer science bibliography, https://dblp.org},
 biburl = {https://dblp.org/rec/conf/aaai/ZhangCL0HLC20.bib},
 booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020},
 pages = {6829--6836},
 publisher = {{AAAI} Press},
 timestamp = {Tue, 02 Feb 2021 00:00:00 +0100},
 title = {AutoShrink: {A} Topology-Aware {NAS} for Discovering Efficient Neural Architecture},
 url = {https://aaai.org/ojs/index.php/AAAI/article/view/6163},
 year = {2020}
}

@inproceedings{zhang2020fast,
 author = {Zhang, Li Lyna and Yang, Yuqing and Jiang, Yuhang and Zhu, Wenwu and Liu, Yunxin},
 booktitle = {2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
 doi = {10.1109/cvprw50498.2020.00354},
 publisher = {IEEE},
 source = {Crossref},
 title = {Fast Hardware-Aware Neural Architecture Search},
 url = {https://doi.org/10.1109/cvprw50498.2020.00354},
 year = {2020}
}

@misc{zhou2021analognets,
 archiveprefix = {arXiv},
 author = {Zhou, Chuteng and Redondo, Fernando Garcia and B\"uchel, Julian and Boybat, Irem and Comas, Xavier Timoneda and Nandakumar, S. R. and Das, Shidhartha and Sebastian, Abu and Gallo, Manuel Le and Whatmough, Paul N.},
 eprint = {2111.06503},
 primaryclass = {cs.AR},
 title = {{AnalogNets:} {Ml-hw} Co-Design of Noise-robust {TinyML} Models and Always-On Analog Compute-in-Memory Accelerator},
 year = {2021}
}

@article{hawks2021psandqs,
 title = {Ps and Qs: Quantization-Aware Pruning for Efficient Low Latency Neural Network Inference},
 volume = {4},
 ISSN = {2624-8212},
 url = {http://dx.doi.org/10.3389/frai.2021.676564},
 DOI = {10.3389/frai.2021.676564},
 journal = {Frontiers in Artificial Intelligence},
 publisher = {Frontiers Media SA},
 author = {Hawks, Benjamin and Duarte, Javier and Fraser, Nicholas J. and Pappalardo, Alessandro and Tran, Nhan and Umuroglu, Yaman},
 year = {2021},
 month = jul 
}