Research Area:  Machine Learning
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.
Author(s) Name:  Yishay Mansour, Mehryar Mohri, Jae Ro, Ananda Theertha Suresh
Journal name:  Computer Science
Publisher name:  arXiv:2002.10619
Paper Link:   https://arxiv.org/abs/2002.10619