Distributed mean estimation with limited communication
作者： Ananda Theertha Suresh , Felix X. Yu , Sanjiv Kumar , H. Brendan McMahan
DOI:
关键词:
摘要: Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean …
arxiv.org
ai.google 参考文章(23)
John N Tsitsiklis, Zhi-Quan Luo, Communication complexity and convex optimization Journal of Complexity. ,vol. 3, pp. 231- 243 ,(1987) , 10.1016/0885-064X(87)90013-6
Kathryn J Horadam, Hadamard Matrices and Their Applications ,(2006)
Ohad Shamir, Yossi Arjevani, Communication Complexity of Distributed Convex Learning and Optimization arXiv: Learning. ,(2015)
Alon Orlitsky, Moein Falahatgar, Ananda Theertha Suresh, Ashkan Jafarpour, Venkatadheeraj Pichapati, Universal Compression of Power-Law Distributions arXiv: Information Theory. ,(2015)
Sanjeev Khudanpur, Daniel Povey, Xiaohui Zhang, Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging international conference on learning representations. ,(2014)
B. Efron, C. Stein, The Jackknife Estimate of Variance Annals of Statistics. ,vol. 9, pp. 586- 596 ,(1981) , 10.1214/AOS/1176345462
R. Krichevsky, V. Trofimov, The performance of universal encoding IEEE Transactions on Information Theory. ,vol. 27, pp. 199- 207 ,(1981) , 10.1109/TIT.1981.1056331
Sanjoy Dasgupta, Anupam Gupta, An elementary proof of a theorem of Johnson and Lindenstrauss Random Structures and Algorithms. ,vol. 22, pp. 60- 65 ,(2003) , 10.1002/RSA.10073
Yishay Mansour, Shai Fine, Avrim Blum, Maria-Florina Balcan, Distributed Learning, Communication Complexity and Privacy arXiv: Learning. ,(2012)
Keith Hall, Ryan McDonald, Gideon Mann, Distributed Training Strategies for the Structured Perceptron north american chapter of the association for computational linguistics. pp. 456- 464 ,(2010)