Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes

Katyusha, 2017, The first direct acceleration of stochastic gradient methods, J. Mach. Learn. Res., 18, 8194 Jr, 1985, Eigenvalues of the laplacian of a graph, Linear Multilinear Algebra, 18, 141, 10.1080/03081088508817681 Beznosikov Boyd, 2006, Randomized gossip algorithms, IEEE Trans. Inf. Theory, 52, 2508, 10.1109/TIT.2006.874516 Chang, 2011, LIBSVM: a library for support vector machines, ACM Trans. Intell. Syst. Technol., 2, 10.1145/1961189.1961199 Gasnikov Gorbunov Hanzely Hanzely Hanzely Hanzely, 2021 Hendrikx Johnson, 2013, Accelerating stochastic gradient descent using predictive variance reduction Kairouz, 2021, Advances and open problems in federated learning, Found. Trends Mach. Learn., 14, 1, 10.1561/2200000083 Konečnỳ Kulkarni, 2020, Survey of personalization techniques for federated learning, 794 Li, 2020, Decentralized accelerated gradient methods with increasing penalty parameters, IEEE Trans. Signal Process., 68, 4855, 10.1109/TSP.2020.3018317 McMahan, 2017, Communication-efficient learning of deep networks from decentralized data, 1273 Nedic, 2009, Distributed subgradient methods for multi-agent optimization, IEEE Trans. Autom. Control, 54, 48, 10.1109/TAC.2008.2009515 Nesterov, 2003 Scaman Shalev-Shwartz, 2014 Smith Tominin Wang Wang