CISPA
Browse

Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow

Download (368.44 kB)
conference contribution
posted on 2024-10-15, 13:11 authored by Xiao ZhangXiao Zhang, Simon S Du, Quanquan Gu
We revisit the inductive matrix completion problem that aims to recover a rank-r matrix with ambient dimension d given n features as the side prior information. The goal is to make use of the known n features to reduce sample and computational complexities. We present and analyze a new gradient-based non-convex optimization algorithm that converges to the true underlying matrix at a linear rate with sample complexity only linearly depending on n and logarithmically depending on d. To the best of our knowledge, all previous algorithms either have a quadratic dependency on the number of features in sample complexity or a sub-linear computational convergence rate. In addition, we provide experiments on both synthetic and real world data to demonstrate the effectiveness of our proposed algorithm.

History

Name of Conference

International Conference on Machine Learning (ICML)

CISPA Affiliation

  • No

BibTeX

@conference{Zhang:Du:Gu:2018, title = "Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow", author = "Zhang, Xiao" AND "Du, Simon S" AND "Gu, Quanquan", year = 2018, month = 7 }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC