Title: Incentive Aligned and Robust Distributed Learning Methods

Abstract: 

Distributed and federated learning enables machine learning algorithms to be trained over decentralized edge devices without requiring the exchange of local datasets. We consider two scenarios in this talk. In the first scenario, we have mostly cooperative agents running distributed optimization methods. We analyze how the distribution of data affects agents' incentives to voluntarily participate and obediently follow traditional federated learning algorithms. We design a Faithful Federated Learning (FFL) mechanism based on FedAvg method and VCG mechanism which achieves (probably approximate) optimality, faithful implementation, voluntary participation, and balanced budget. We then analyze an alternative approach to align individual agent’s incentive to participate by allowing them to opt in or out. We propose a game theoretic framework and study the equilibrium properties with both rational and bounded rational agents. In the second scenario, we turn to a game theoretic formulation, where the agents may be under attack. We characterize the tradeoffs between convergence speed and robustness of learning dynamics. 

Bio: 

Ermin Wei is an Associate Professor at the Electrical and Computer Engineering Department and Industrial Engineering and Management Sciences Department of Northwestern University. She completed her PhD studies in Electrical Engineering and Computer Science at MIT in 2014, advised by Professor Asu Ozdaglar, where she also obtained her M.S. She received her undergraduate triple degree in Computer Engineering, Finance and Mathematics with a minor in German, from University of Maryland, College Park. Her team won the 2nd place in the GO-competition Challenge 1, an electricity grid optimization competition organized by Department of Energy. Wei's research interests include distributed optimization methods, convex optimization and analysis, smart grid, communication systems and energy networks and market economic analysis.