@inproceedings{7437, abstract = {Most of today's distributed machine learning systems assume reliable networks: whenever two machines exchange information (e.g., gradients or models), the network should guarantee the delivery of the message. At the same time, recent work exhibits the impressive tolerance of machine learning algorithms to errors or noise arising from relaxed communication or synchronization. In this paper, we connect these two trends, and consider the following question: Can we design machine learning systems that are tolerant to network unreliability during training? With this motivation, we focus on a theoretical problem of independent interest-given a standard distributed parameter server architecture, if every communication between the worker and the server has a non-zero probability p of being dropped, does there exist an algorithm that still converges, and at what speed? The technical contribution of this paper is a novel theoretical analysis proving that distributed learning over unreliable network can achieve comparable convergence rate to centralized or distributed learning over reliable networks. Further, we prove that the influence of the packet drop rate diminishes with the growth of the number of parameter servers. We map this theoretical result onto a real-world scenario, training deep neural networks over an unreliable network layer, and conduct network simulation to validate the system improvement by allowing the networks to be unreliable.}, author = {Yu, Chen and Tang, Hanlin and Renggli, Cedric and Kassing, Simon and Singla, Ankit and Alistarh, Dan-Adrian and Zhang, Ce and Liu, Ji}, booktitle = {36th International Conference on Machine Learning, ICML 2019}, isbn = {9781510886988}, location = {Long Beach, CA, United States}, pages = {12481--12512}, publisher = {IMLS}, title = {{Distributed learning over unreliable networks}}, volume = {2019-June}, year = {2019}, }