MOSES: A Streaming Algorithm for Linear Dimensionality Reduction

06/04/2018
by   Armin Eftekhari, et al.
0

This paper introduces Memory-limited Online Subspace Estimation Scheme (MOSES) for both estimating the principal components of data and reducing its dimension. More specifically, consider a scenario where the data vectors are presented sequentially to a user who has limited storage and processing time available, for example in the context of sensor networks. In this scenario, MOSES maintains an estimate of leading principal components of the data that has arrived so far and also reduces its dimension. In terms of its origins, MOSES slightly generalises the popular incremental Singular Vale Decomposition (SVD) to handle thin blocks of data. This simple generalisation is in part what allows us to complement MOSES with a comprehensive statistical analysis that is not available for incremental SVD, despite its empirical success. This generalisation also enables us to concretely interpret MOSES as an approximate solver for the underlying non-convex optimisation program. We also find that MOSES shows state-of-the-art performance in our numerical experiments with both synthetic and real-world datasets.

READ FULL TEXT
research
07/21/2013

On GROUSE and Incremental SVD

GROUSE (Grassmannian Rank-One Update Subspace Estimation) is an incremen...
research
08/06/2018

Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching

Big data problems frequently require processing datasets in a streaming ...
research
05/02/2018

TR-SVD: Fast and Memory Efficient Method for Time Ranged Singular Value Decomposition

Given multiple time series data, how can we efficiently find latent patt...
research
05/02/2018

Zoom-SVD: Fast and Memory Efficient Method for Extracting Key Patterns in an Arbitrary Time Range

Given multiple time series data, how can we efficiently find latent patt...
research
09/23/2017

On Principal Components Regression, Random Projections, and Column Subsampling

Principal Components Regression (PCR) is a traditional tool for dimensio...
research
04/11/2022

An answer to an open question in the incremental SVD

Incremental singular value decomposition (SVD) was proposed by Brand to ...
research
08/29/2023

An Incremental SVD Method for Non-Fickian Flows in Porous Media: Addressing Storage and Computational Challenges

It is well known that the numerical solution of the Non-Fickian flows at...

Please sign up or login with your details

Forgot password? Click here to reset