← Back to papers
2013 NIPS NeurIPS 2013

Stochastic Optimization of PCA with Capped MSG

Abstract

We study PCA as a stochastic optimization problem and propose a novel stochastic approximation algorithm which we refer to as Matrix Stochastic Gradient'' (MSG), as well as a practical variant, Capped MSG. We study the method both theoretically and empirically. "

🌉 Interdisciplinary Bridge — Machine Learning and Mathematics & Optimization
🧭 Keyword Pioneer — matrix stochastic gradient
🐣 Hot Topic Early Bird — stochastic optimization
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio
📈 Trend Setter — Stochastic Methods

Authors

Raman Arora , Andy Cotter , Nati Srebro

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Optimization Mathematics & Optimization > Optimization > Stochastic Methods Machine Learning > Core Methods > Dimensionality Reduction Machine Learning > Optimization & Theory > Stochastic Methods Machine Learning > Core Methods > Optimization Deep Learning > Optimization & Theory > Stochastic Methods

Keywords

stochastic optimization dimensionality reduction stochastic gradient principal component analysis matrix factorization gradient descent matrix stochastic gradient
Download PDF

Related papers

Latent Structured Active Learning 2013
On Flat versus Hierarchical Classification in Large-Scale Taxonomies 2013
Generalized Method-of-Moments for Rank Aggregation 2013
Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections 2013
Accelerated Mini-Batch Stochastic Dual Coordinate Ascent 2013