Timezone: »

 
Poster
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
Steve Chien · Prateek Jain · Walid Krichene · Steffen Rendle · Shuang Song · Abhradeep Guha Thakurta · Li Zhang

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 5 »

We study the problem of differentially private (DP) matrix completion under user-level privacy. We design a joint differentially private variant of the popular Alternating-Least-Squares (ALS) method that achieves: i) (nearly) optimal sample complexity for matrix completion (in terms of number of items, users), and ii) the best known privacy/utility trade-off both theoretically, as well as on benchmark data sets. In particular, we provide the first global convergence analysis of ALS with noise introduced to ensure DP, and show that, in comparison to the best known alternative (the Private Frank-Wolfe algorithm by Jain et al. (2018)), our error bounds scale significantly better with respect to the number of items and users, which is critical in practical problems. Extensive validation on standard benchmarks demonstrate that the algorithm, in combination with carefully designed sampling procedures, is significantly more accurate than existing techniques, thus promising to be the first practical DP embedding model.

Keywords: Privacy, Anonymity, and Security · Theory · Spaces of Functions and Kernels · Deep Learning; Deep Learning -> CNN Architectures; Theory · Social Aspects of Machine Learning

Author Information

Steve Chien (Google)
Prateek Jain (Google Research)
Walid Krichene (Google Research)
Steffen Rendle (Google)
Shuang Song (Google)
Abhradeep Guha Thakurta (Google)
Li Zhang (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors