@inproceedings{crankshaw2017clipper, title={Clipper: A ${$Low-Latency$}$ Online Prediction Serving System}, author={Crankshaw, Daniel and Wang, Xin and Zhou, Guilio and Franklin, Michael J and Gonzalez, Joseph E and Stoica, Ion}, booktitle={14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)}, pages={613--627}, year={2017} }

@inproceedings{qin2019swift, title={Swift machine learning model serving scheduling: a region based reinforcement learning approach}, author={Qin, Heyang and Zawad, Syed and Zhou, Yanqi and Yang, Lei and Zhao, Dongfang and Yan, Feng}, booktitle={Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis}, pages={1--23}, year={2019} }

@inproceedings{yadwadkar2019case, title={A case for managed and model-less inference serving}, author={Yadwadkar, Neeraja J and Romero, Francisco and Li, Qian and Kozyrakis, Christos}, booktitle={Proceedings of the Workshop on Hot Topics in Operating Systems}, pages={184--191}, year={2019} }

@inproceedings{zhang2019mark, title={${$MArk$}$: Exploiting Cloud Services for ${$Cost-Effective$}$,${$SLO-Aware$}$ Machine Learning Inference Serving}, author={Zhang, Chengliang and Yu, Minchen and Wang, Wei and Yan, Feng}, booktitle={2019 USENIX Annual Technical Conference (USENIX ATC 19)}, pages={1049--1062}, year={2019} }

@inproceedings{zhang2020model, title={${$Model-Switching$}$: Dealing with Fluctuating Workloads in ${$Machine-Learning-as-a-Service$}$ Systems}, author={Zhang, Jeff and Elnikety, Sameh and Zarar, Shuayb and Gupta, Atul and Garg, Siddharth}, booktitle={12th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 20)}, year={2020} }

@inproceedings{lee2018pretzel, title={${$PRETZEL$}$: Opening the black box of machine learning prediction serving systems}, author={Lee, Yunseong and Scolari, Alberto and Chun, Byung-Gon and Santambrogio, Marco Domenico and Weimer, Markus and Interlandi, Matteo}, booktitle={13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)}, pages={611--626}, year={2018} }

@inproceedings{schelter2020learning, title={Learning to validate the predictions of black box classifiers on unseen data}, author={Schelter, Sebastian and Rukat, Tammo and Biessmann, Felix}, booktitle={Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data}, pages={1289--1299}, year={2020} }

@inproceedings{breck2019data, title={Data Validation for Machine Learning.}, author={Breck, Eric and Polyzotis, Neoklis and Roy, Sudip and Whang, Steven and Zinkevich, Martin}, booktitle={MLSys}, year={2019} }

@inproceedings{choi2021lazy, title={Lazy Batching: An SLA-aware batching system for cloud machine learning inference}, author={Choi, Yujeong and Kim, Yunseong and Rhu, Minsoo}, booktitle={2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA)}, pages={493--506}, year={2021}, organization={IEEE} }

@inproceedings{hu2021scrooge, title={Scrooge: A Cost-Effective Deep Learning Inference System}, author={Hu, Yitao and Ghosh, Rajrup and Govindan, Ramesh}, booktitle={Proceedings of the ACM Symposium on Cloud Computing}, pages={624--638}, year={2021} }

@article{hudistributed, title={Distributed Inference with Deep Learning Models across Heterogeneous Edge Devices}, author={Hu, Chenghao and Li, Baochun} }

@article{mendez2022edge, title={Edge Intelligence: Concepts, architectures, applications and future directions}, author={Mendez, Javier and Bierzynski, Kay and Cu{'e}llar, MP and Morales, Diego P}, journal={ACM Transactions on Embedded Computing Systems (TECS)}, year={2022}, publisher={ACM New York, NY} }

@inproceedings{gunasekaran2022cocktail, title={Cocktail: A Multidimensional Optimization for Model Serving in Cloud}, author={Gunasekaran, Jashwant Raj and Mishra, Cyan Subhra and Thinakaran, Prashanth and Sharma, Bikash and Kandemir, Mahmut Taylan and Das, Chita R}, booktitle={19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)}, pages={1041--1057}, year={2022} }

@article{mao2022differentiate, title={Differentiate Quality of Experience Scheduling for Deep Learning Inferences with Docker Containers in the Cloud}, author={Mao, Ying and Yan, Weifeng and Song, Yun and Zeng, Yue and Chen, Ming and Cheng, Long and Liu, Qingzhi}, journal={IEEE Transactions on Cloud Computing}, year={2022}, publisher={IEEE} }

@inproceedings{romero2021infaas, title={${$INFaaS$}$: Automated Model-less Inference Serving}, author={Romero, Francisco and Li, Qian and Yadwadkar, Neeraja J and Kozyrakis, Christos}, booktitle={2021 USENIX Annual Technical Conference (USENIX ATC 21)}, pages={397--411}, year={2021} }

@inproceedings{gujarati2017swayam, title={Swayam: distributed autoscaling to meet slas of machine learning inference services with resource efficiency}, author={Gujarati, Arpan and Elnikety, Sameh and He, Yuxiong and McKinley, Kathryn S and Brandenburg, Bj{"o}rn B}, booktitle={Proceedings of the 18th ACM/IFIP/USENIX Middleware Conference}, pages={109--120}, year={2017} }

@inproceedings{crankshaw2020inferline, title={InferLine: latency-aware provisioning and scaling for prediction serving pipelines}, author={Crankshaw, Daniel and Sela, Gur-Eyal and Mo, Xiangxi and Zumar, Corey and Stoica, Ion and Gonzalez, Joseph and Tumanov, Alexey}, booktitle={Proceedings of the 11th ACM Symposium on Cloud Computing}, pages={477--491}, year={2020} }

@inproceedings{soifer2019deep, title={Deep learning inference service at microsoft}, author={Soifer, Jonathan and Li, Jason and Li, Mingqin and Zhu, Jeffrey and Li, Yingnan and He, Yuxiong and Zheng, Elton and Oltean, Adi and Mosyak, Maya and Barnes, Chris and others}, booktitle={2019 USENIX Conference on Operational Machine Learning (OpML 19)}, pages={15--17}, year={2019} }

@article{mallick2022matchmaker, title={Matchmaker: Data Drift Mitigation in Machine Learning for Large-Scale Systems}, author={Mallick, Ankur and Hsieh, Kevin and Arzani, Behnaz and Joshi, Gauri}, journal={Proceedings of Machine Learning and Systems}, volume={4}, year={2022} }

@article{xie2022cost, title={Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach}, author={Xie, Shuzhao and Xue, Yuan and Zhu, Yifei and Wang, Zhi}, journal={arXiv preprint arXiv:2204.13971}, year={2022} }

	○ OSDI
	○ NSDI
	○ SOSP
	○ ATC
	○ EuroSys
	○ MLSYS: top conference for machine learning and system

	○ https://mlsys.stanford.edu/

https://github.com/HuaizhengZhang/Awesome-System-for-Machine-Learning