mirror of
https://github.com/openmlsys/openmlsys-zh.git
synced 2026-04-03 02:38:57 +08:00
282 lines
10 KiB
BibTeX
282 lines
10 KiB
BibTeX
@article{rosenblatt1958perceptron,
|
|
title={The perceptron: a probabilistic model for information storage and organization in the brain.},
|
|
author={Rosenblatt, Frank},
|
|
journal={Psychological Review},
|
|
volume={65},
|
|
number={6},
|
|
pages={386},
|
|
year={1958},
|
|
publisher={American Psychological Association}
|
|
}
|
|
|
|
@article{lecun1989backpropagation,
|
|
title={Backpropagation applied to handwritten zip code recognition},
|
|
author={LeCun, Yann and Boser, Bernhard and Denker, John S and Henderson, Donnie and Howard, Richard E and Hubbard, Wayne and Jackel, Lawrence D},
|
|
journal={Neural computation},
|
|
volume={1},
|
|
number={4},
|
|
pages={541--551},
|
|
year={1989},
|
|
publisher={MIT Press}
|
|
}
|
|
|
|
@inproceedings{krizhevsky2012imagenet,
|
|
title={Imagenet classification with deep convolutional neural networks},
|
|
author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
|
|
booktitle={Advances in Neural Information Processing Systems},
|
|
pages={1097--1105},
|
|
year={2012}
|
|
}
|
|
|
|
@inproceedings{he2016deep,
|
|
title={{Deep Residual Learning for Image Recognition}},
|
|
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
|
|
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
|
|
year={2016}
|
|
}
|
|
|
|
@article{rumelhart1986learning,
|
|
title={Learning representations by back-propagating errors},
|
|
author={Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J},
|
|
journal={Nature},
|
|
volume={323},
|
|
number={6088},
|
|
pages={533},
|
|
year={1986},
|
|
publisher={Nature Publishing Group}
|
|
}
|
|
|
|
@article{Hochreiter1997lstm,
|
|
author = {Hochreiter, Sepp and Hochreiter, S and Schmidhuber, J{\"{u}}rgen and Schmidhuber, J},
|
|
isbn = {08997667 (ISSN)},
|
|
issn = {0899-7667},
|
|
journal = {Neural Computation},
|
|
number = {8},
|
|
pages = {1735--80},
|
|
pmid = {9377276},
|
|
title = {{Long Short-Term Memory.}},
|
|
volume = {9},
|
|
year = {1997}
|
|
}
|
|
|
|
@inproceedings{vaswani2017attention,
|
|
title={Attention is all you need},
|
|
author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
|
|
booktitle={Advances in Neural Information Processing Systems},
|
|
pages={5998--6008},
|
|
year={2017}
|
|
}
|
|
|
|
@article{lecun2015deep,
|
|
title={Deep learning},
|
|
author={LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
|
|
journal={Nature},
|
|
volume={521},
|
|
number={7553},
|
|
pages={436},
|
|
year={2015},
|
|
publisher={Nature Publishing Group}
|
|
}
|
|
|
|
@inproceedings{KingmaAdam2014,
|
|
title = {{Adam}: A Method for Stochastic Optimization},
|
|
author = {Kingma, Diederik and Ba, Jimmy},
|
|
booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
|
|
year = {2014}
|
|
}
|
|
|
|
@techreport{tieleman2012rmsprop,
|
|
title={Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning},
|
|
author={Tieleman, T and Hinton, G},
|
|
year={2017},
|
|
institution={Technical Report}
|
|
}
|
|
|
|
@article{duchi2011adagrad,
|
|
title={Adaptive subgradient methods for online learning and stochastic optimization},
|
|
author={Duchi, John and Hazan, Elad and Singer, Yoram},
|
|
journal={Journal of Machine Learning Research (JMLR)},
|
|
volume={12},
|
|
number={Jul},
|
|
pages={2121--2159},
|
|
year={2011}
|
|
}
|
|
|
|
@inproceedings{meijer2006linq,
|
|
title={Linq: reconciling object, relations and xml in the. net framework},
|
|
author={Meijer, Erik and Beckman, Brian and Bierman, Gavin},
|
|
booktitle={Proceedings of the 2006 ACM SIGMOD international conference on Management of data},
|
|
pages={706--706},
|
|
year={2006}
|
|
}
|
|
|
|
@inproceedings{murray2013naiad,
|
|
title={Naiad: a timely dataflow system},
|
|
author={Murray, Derek G and McSherry, Frank and Isaacs, Rebecca and Isard, Michael and Barham, Paul and Abadi, Mart{\'\i}n},
|
|
booktitle={Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles},
|
|
pages={439--455},
|
|
year={2013}
|
|
}
|
|
|
|
@inproceedings{mnih2016asynchronous,
|
|
title={Asynchronous methods for deep reinforcement learning},
|
|
author={Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
|
|
booktitle={International Conference on Machine Learning (ICML)},
|
|
pages={1928--1937},
|
|
year={2016}
|
|
}
|
|
|
|
@article{espeholt2018impala,
|
|
title={Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures},
|
|
author={Espeholt, Lasse and Soyer, Hubert and Munos, Remi and Simonyan, Karen and Mnih, Volodymir and Ward, Tom and Doron, Yotam and Firoiu, Vlad and Harley, Tim and Dunning, Iain and others},
|
|
journal={arXiv preprint arXiv:1802.01561},
|
|
year={2018}
|
|
}
|
|
|
|
@article{espeholt2019seed,
|
|
title={Seed rl: Scalable and efficient deep-rl with accelerated central inference},
|
|
author={Espeholt, Lasse and Marinier, Rapha{\"e}l and Stanczyk, Piotr and Wang, Ke and Michalski, Marcin},
|
|
journal={arXiv preprint arXiv:1910.06591},
|
|
year={2019}
|
|
}
|
|
|
|
@misc{horgan2018distributed,
|
|
title={Distributed Prioritized Experience Replay},
|
|
author={Dan Horgan and John Quan and David Budden and Gabriel Barth-Maron and Matteo Hessel and Hado van Hasselt and David Silver},
|
|
year={2018},
|
|
eprint={1803.00933},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.LG}
|
|
}
|
|
|
|
@inproceedings{moritz2018ray,
|
|
title={Ray: A distributed framework for emerging $\{$AI$\}$ applications},
|
|
author={Moritz, Philipp and Nishihara, Robert and Wang, Stephanie and Tumanov, Alexey and Liaw, Richard and Liang, Eric and Elibol, Melih and Yang, Zongheng and Paul, William and Jordan, Michael I and others},
|
|
booktitle={13th $\{$USENIX$\}$ Symposium on Operating Systems Design and Implementation ($\{$OSDI$\}$ 18)},
|
|
pages={561--577},
|
|
year={2018}
|
|
}
|
|
|
|
@inproceedings{zaharia2010spark,
|
|
title={Spark: Cluster computing with working sets},
|
|
author={Zaharia, Matei and Chowdhury, Mosharaf and Franklin, Michael J and Shenker, Scott and Stoica, Ion},
|
|
booktitle={2nd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 10)},
|
|
year={2010}
|
|
}
|
|
|
|
@article{fetterly2009dryadlinq,
|
|
title={DryadLINQ: A system for general-purpose distributed data-parallel computing using a high-level language},
|
|
author={Fetterly, Yuan Yu Michael Isard Dennis and Budiu, Mihai and Erlingsson, {\'U}lfar and Currey, Pradeep Kumar Gunda Jon},
|
|
journal={Proc. LSDS-IR},
|
|
volume={8},
|
|
year={2009}
|
|
}
|
|
|
|
@article{murray2021tf,
|
|
title={tf. data: A machine learning data processing framework},
|
|
author={Murray, Derek G and Simsa, Jiri and Klimovic, Ana and Indyk, Ihor},
|
|
journal={arXiv preprint arXiv:2101.12127},
|
|
year={2021}
|
|
}
|
|
|
|
@article{mohan2020analyzing,
|
|
title={Analyzing and mitigating data stalls in dnn training},
|
|
author={Mohan, Jayashree and Phanishayee, Amar and Raniwala, Ashish and Chidambaram, Vijay},
|
|
journal={arXiv preprint arXiv:2007.06775},
|
|
year={2020}
|
|
}
|
|
|
|
@misc{rmpygil
|
|
author = "Sam Gross",
|
|
title = "Multithreaded Python without the GIL",
|
|
howpublished = "Website",
|
|
year = {2021},
|
|
note = {\url{https://docs.google.com/document/d/18CXhDb1ygxg-YXNBJNzfzZsDFosB5e6BfnXLlejd9l0/edit#heading=h.kcngwrty1lv}}
|
|
}
|
|
|
|
@misc{nvidia_dali
|
|
author = "NVIDIA",
|
|
title = "DALI",
|
|
howpublished = "Website",
|
|
year = {2018},
|
|
note = {\url{https://github.com/NVIDIA/DALI}}
|
|
}
|
|
|
|
@misc{minddata
|
|
author = "HuaWei",
|
|
title = "Dataset Plugin",
|
|
howpublished = "Website",
|
|
year = {2020},
|
|
note = {\url{https://gitee.com/mindspore/dataset-plugin}}
|
|
}
|
|
|
|
@article{liang2017ray,
|
|
title={Ray rllib: A composable and scalable reinforcement learning library},
|
|
author={Liang, Eric and Liaw, Richard and Nishihara, Robert and Moritz, Philipp and Fox, Roy and Gonzalez, Joseph and Goldberg, Ken and Stoica, Ion},
|
|
journal={arXiv preprint arXiv:1712.09381},
|
|
pages={85},
|
|
year={2017}
|
|
}
|
|
|
|
@article{cassirer2021reverb,
|
|
title={Reverb: A Framework For Experience Replay},
|
|
author={Cassirer, Albin and Barth-Maron, Gabriel and Brevdo, Eugene and Ramos, Sabela and Boyd, Toby and Sottiaux, Thibault and Kroiss, Manuel},
|
|
journal={arXiv preprint arXiv:2102.04736},
|
|
year={2021}
|
|
}
|
|
|
|
@article{hoffman2020acme,
|
|
title={Acme: A research framework for distributed reinforcement learning},
|
|
author={Hoffman, Matt and Shahriari, Bobak and Aslanides, John and Barth-Maron, Gabriel and Behbahani, Feryal and Norman, Tamara and Abdolmaleki, Abbas and Cassirer, Albin and Yang, Fan and Baumli, Kate and others},
|
|
journal={arXiv preprint arXiv:2006.00979},
|
|
year={2020}
|
|
}
|
|
|
|
@article{ding2020efficient,
|
|
title={Efficient Reinforcement Learning Development with RLzoo},
|
|
author={Ding, Zihan and Yu, Tianyang and Huang, Yanhua and Zhang, Hongming and Li, Guo and Guo, Quancheng and Mai, Luo and Dong, Hao},
|
|
journal={arXiv preprint arXiv:2009.08644},
|
|
year={2020}
|
|
}
|
|
|
|
@article{makoviychuk2021isaac,
|
|
title={Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning},
|
|
author={Makoviychuk, Viktor and Wawrzyniak, Lukasz and Guo, Yunrong and Lu, Michelle and Storey, Kier and Macklin, Miles and Hoeller, David and Rudin, Nikita and Allshire, Arthur and Handa, Ankur and others},
|
|
journal={arXiv preprint arXiv:2108.10470},
|
|
year={2021}
|
|
}
|
|
|
|
@article{vinyals2019grandmaster,
|
|
title={Grandmaster level in StarCraft II using multi-agent reinforcement learning},
|
|
author={Vinyals, Oriol and Babuschkin, Igor and Czarnecki, Wojciech M and Mathieu, Micha{\"e}l and Dudzik, Andrew and Chung, Junyoung and Choi, David H and Powell, Richard and Ewalds, Timo and Georgiev, Petko and others},
|
|
journal={Nature},
|
|
volume={575},
|
|
number={7782},
|
|
pages={350--354},
|
|
year={2019},
|
|
publisher={Nature Publishing Group}
|
|
}
|
|
|
|
@article{berner2019dota,
|
|
title={Dota 2 with large scale deep reinforcement learning},
|
|
author={Berner, Christopher and Brockman, Greg and Chan, Brooke and Cheung, Vicki and D{\k{e}}biak, Przemys{\l}aw and Dennison, Christy and Farhi, David and Fischer, Quirin and Hashme, Shariq and Hesse, Chris and others},
|
|
journal={arXiv preprint arXiv:1912.06680},
|
|
year={2019}
|
|
}
|
|
|
|
@article{han2020tstarbot,
|
|
title={Tstarbot-x: An open-sourced and comprehensive study for efficient league training in starcraft ii full game},
|
|
author={Han, Lei and Xiong, Jiechao and Sun, Peng and Sun, Xinghai and Fang, Meng and Guo, Qingwei and Chen, Qiaobo and Shi, Tengfei and Yu, Hongsheng and Wu, Xipeng and others},
|
|
journal={arXiv preprint arXiv:2011.13729},
|
|
year={2020}
|
|
}
|
|
|
|
@inproceedings{wang2021scc,
|
|
title={SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II},
|
|
author={Wang, Xiangjun and Song, Junxiao and Qi, Penghui and Peng, Peng and Tang, Zhenkun and Zhang, Wei and Li, Weimin and Pi, Xiongjun and He, Jujie and Gao, Chao and others},
|
|
booktitle={International Conference on Machine Learning},
|
|
pages={10905--10915},
|
|
year={2021},
|
|
organization={PMLR}
|
|
}
|