@inproceedings{kong_consensus_2021,
	series = {Proceedings of {Machine} {Learning} {Research}},
	title = {Consensus {Control} for {Decentralized} {Deep} {Learning}},
	volume = {139},
	url = {https://proceedings.mlr.press/v139/kong21a.html},
	abstract = {Decentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal that, even in a data-center setup, decentralized training often suffers from the degradation in the quality of the model: the training and test performance of models trained in a decentralized fashion is in general worse than that of models trained in a centralized fashion, and this performance drop is impacted by parameters such as network size, communication topology and data partitioning.},
	language = {en},
	booktitle = {Proceedings of the 38th {International} {Conference} on {Machine} {Learning}},
	publisher = {PMLR},
	author = {Kong, Lingjing and Lin, Tao and Koloskova, Anastasia and Jaggi, Martin and Stich, Sebastian U},
	year = {2021},
	pages = {5686--5696},
}