Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
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 ot...
Gespeichert in:
Hauptverfasser: | , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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-$r$ and a $k$-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. |
---|---|
DOI: | 10.48550/arxiv.2210.03505 |