Timezone: »

Distributed Personalized Empirical Risk Minimization
Yuyang Deng · Mohammad Mahdi Kamani · Pouria Mahdavinia · Mehrdad Mahdavi

Wed Dec 13 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #1120

This paper advocates a new paradigm Personalized Empirical Risk Minimization (PERM) to facilitate learning from heterogeneous data sources without imposing stringent constraints on computational resources shared by participating devices. In PERM, we aim at learning a distinct model for each client by personalizing the aggregation of local empirical losses by effectively estimating the statistical discrepancy among data distributions, which entails optimal statistical accuracy for all local distributions and overcomes the data heterogeneity issue. To learn personalized models at scale, we propose a distributed algorithm that replaces the standard model averaging with model shuffling to simultaneously optimize PERM objectives for all devices. This also allows to learn distinct model architectures (e.g., neural networks with different number of parameters) for different clients, thus confining to underlying memory and compute resources of individual clients. We rigorously analyze the convergence of proposed algorithm and conduct experiments that corroborates the effectiveness of proposed paradigm.

Author Information

Yuyang Deng (Penn State)
Mohammad Mahdi Kamani (Wyze Labs)
Pouria Mahdavinia (Penn State University)
Mehrdad Mahdavi (Pennsylvania State University)

Mehrdad Mahdavi is an Assistant Professor of Computer Science & Engineering at Pennsylvania State University. He runs the Machine Learning and Optimization Lab, where they work on fundamental problems in computational and theoretical machine learning.

More from the Same Authors