The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per user. In this work, we present a systematic learning-theoretic study of personalization. We propose and analyze three approaches: user clustering, data interpolation, and model interpolation. For all three approaches, we provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance empirically. All of our algorithms are model-agnostic and work for any hypothesis class.
@article{arxiv.2002.10619,
title = {Three Approaches for Personalization with Applications to Federated Learning},
author = {Yishay Mansour and Mehryar Mohri and Jae Ro and Ananda Theertha Suresh},
journal= {arXiv preprint arXiv:2002.10619},
year = {2020}
}