Representation of Federated Learning via Worst-Case Robust Optimization Theory

Federated learning (FL) is a distributed learning approach where a set of end-user devices participate in the learning process by acting on their isolated local data sets. Here, we process local data sets of users where worst-case optimization theory is used to reformulate the FL problem where the impact of local data sets in training phase is considered as an uncertain function bounded in a closed uncertainty region. This representation allows us to compare the performance of FL with its centralized counterpart, and to replace the uncertain function with a concept of protection functions leading to more tractable formulation. The latter supports applying a regularization factor in each user cost function in FL to reach a better performance. We evaluated our model using the MNIST data set versus the protection function parameters, e.g., regularization factors.

[1]  John N. Tsitsiklis,et al.  Parallel and distributed computation , 1989 .

[2]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[3]  A Ben Tal,et al.  ROBUST SOLUTIONS TO UNCERTAIN PROGRAMS , 1999 .

[4]  Tian Li,et al.  Fair Resource Allocation in Federated Learning , 2019, ICLR.

[5]  Peter Richtárik,et al.  Federated Optimization: Distributed Machine Learning for On-Device Intelligence , 2016, ArXiv.

[6]  Melvyn Sim,et al.  Robust linear optimization under general norms , 2004, Oper. Res. Lett..

[7]  Yonina C. Eldar,et al.  Convex Optimization in Signal Processing and Communications , 2009 .

[8]  Francisco Facchinei,et al.  Hybrid Random/Deterministic Parallel Algorithms for Convex and Nonconvex Big Data Optimization , 2014, IEEE Transactions on Signal Processing.

[9]  Gregory Cohen,et al.  EMNIST: an extension of MNIST to handwritten letters , 2017, CVPR 2017.

[10]  Qiang Yang,et al.  Federated Machine Learning , 2019, ACM Trans. Intell. Syst. Technol..

[11]  Mihaela van der Schaar,et al.  Robust Additively Coupled Games in the Presence of Bounded Uncertainty in Communication Networks , 2014, IEEE Transactions on Vehicular Technology.

[12]  Francisco Facchinei,et al.  Parallel and Distributed Methods for Constrained Nonconvex Optimization—Part I: Theory , 2016, IEEE Transactions on Signal Processing.

[13]  Saeedeh Parsaeefard,et al.  Robust Resource Allocation in Future Wireless Networks , 2017 .

[14]  F. Facchinei,et al.  Finite-Dimensional Variational Inequalities and Complementarity Problems , 2003 .

[15]  Zhi-Quan Luo,et al.  A Unified Convergence Analysis of Block Successive Minimization Methods for Nonsmooth Optimization , 2012, SIAM J. Optim..

[16]  Francisco Facchinei,et al.  Asynchronous parallel algorithms for nonconvex optimization , 2016, Mathematical Programming.

[17]  Anit Kumar Sahu,et al.  Federated Optimization in Heterogeneous Networks , 2018, MLSys.