English

Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components

Machine Learning 2023-09-07 v3 Cryptography and Security Optimization and Control Machine Learning

Abstract

Personalization of machine learning (ML) predictions for individual users/domains/enterprises is critical for practical recommendation systems. Standard personalization approaches involve learning a user/domain specific embedding that is fed into a fixed global model which can be limiting. On the other hand, personalizing/fine-tuning model itself for each user/domain -- a.k.a meta-learning -- has high storage/infrastructure cost. Moreover, rigorous theoretical studies of scalable personalization approaches have been very limited. To address the above issues, we propose a novel meta-learning style approach that models network weights as a sum of low-rank and sparse components. This captures common information from multiple individuals/users together in the low-rank part while sparse part captures user-specific idiosyncrasies. We then study the framework in the linear setting, where the problem reduces to that of estimating the sum of a rank-rr and a kk-column sparse matrix using a small number of linear measurements. We propose a computationally efficient alternating minimization method with iterative hard thresholding -- AMHT-LRS -- to learn the low-rank and sparse part. Theoretically, for the realizable Gaussian data setting, we show that AMHT-LRS solves the problem efficiently with nearly optimal sample complexity. Finally, a significant challenge in personalization is ensuring privacy of each user's sensitive data. We alleviate this problem by proposing a differentially private variant of our method that also is equipped with strong generalization guarantees.

Keywords

Cite

@article{arxiv.2210.03505,
  title  = {Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components},
  author = {Soumyabrata Pal and Prateek Varshney and Prateek Jain and Abhradeep Guha Thakurta and Gagan Madan and Gaurav Aggarwal and Pradeep Shenoy and Gaurav Srivastava},
  journal= {arXiv preprint arXiv:2210.03505},
  year   = {2023}
}

Comments

104 pages, 7 figures, 2 Tables

R2 v1 2026-06-28T02:59:55.832Z