Distributed matrix completion and robust factorization

MaRDI QIDQ5502138zbMATH OpenFDO

Authors Lester Mackey, Ameet Talwalkar, Michael Jordan

Publication date 17 August 2015

Full work available at URL https://arxiv.org/abs/1107.0789, http://jmlr.csail.mit.edu/papers/v16/mackey15a.html

zbMATH Keywords

collaborative filteringdistributed algorithmsdivide-and-conquermatrix completionmatrix factorizationparallel algorithmsrandomized algorithmsrobust matrix factorizationvideo surveillance

Mathematics Subject Classification ID

Factorization of matrices (15A23) Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10) Distributed algorithms (68W15) Randomized algorithms (68W20)

Abstract: If learning methods are to scale to the massive sizes of modern datasets, it is essential for the field of machine learning to embrace parallel and distributed computing. Inspired by the recent development of matrix factorization methods with rich theory but poor computational complexity and by the relative ease of mapping matrices onto distributed architectures, we introduce a scalable divide-and-conquer framework for noisy matrix factorization. We present a thorough theoretical analysis of this framework in which we characterize the statistical errors introduced by the "divide" step and control their magnitude in the "conquer" step, so that the overall algorithm enjoys high-probability estimation guarantees comparable to those of its base algorithm. We also present experiments in collaborative filtering and video background modeling that demonstrate the near-linear to superlinear speed-ups attainable with this approach.

Recommendations

• Parallel stochastic gradient algorithms for large-scale matrix completion
• Distributed Bayesian matrix factorization with limited communication
• Matrix completion and low-rank SVD via fast alternating least squares
• Spectral regularization algorithms for learning large incomplete matrices
• Online learning for matrix factorization and sparse coding

Cited in

(20)

• A distributed Frank-Wolfe framework for learning low-rank matrices with the trace norm
• A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning
• Communication-efficient distributed \(M\)-estimation with missing data
• Distributed Bayesian matrix factorization with limited communication
• LIBMF: a library for parallel matrix factorization in shared-memory systems
• Distributed Orthogonal Factorization: Givens and Householder Algorithms
• Parallelizing spectrally regularized kernel algorithms
• Robust PCA by manifold optimization
• Distributed Robust Subspace Recovery
• A distributed and integrated method of moments for high-dimensional correlated data analysis
• Partitioned Approach for High-dimensional Confidence Intervals with Large Split Sizes
• scientific article; zbMATH DE number 7626717 (Why is no real title available?)
• Doubly distributed supervised learning and inference with high-dimensional correlated outcomes
• Decomposition into low-rank plus additive matrices for background/foreground separation: a review for a comparative evaluation with a large-scale dataset
• scientific article; zbMATH DE number 7164697 (Why is no real title available?)
• Communication-efficient distributed statistical inference
• CEDAR: Communication Efficient Distributed Analysis for Regressions
• Decentralized Gradient-Quantization Based Matrix Factorization for Fast Privacy-Preserving Point-of-Interest Recommendation
• Meta Clustering for Collaborative Learning
• Enhancements of communication-efficient distributed statistical inference and its privacy preservation

Describes a project that uses

Uses Software

• Jellyfish
• HOGWILD

This page was built for publication: Distributed matrix completion and robust factorization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5502138)