CS 267 Final Project: Parallel Robust PCA
نویسندگان
چکیده
Principal Component Analysis (PCA; Pearson, 1901) is a widely used method for data compression. The goal is to find the best low rank approximation of a given matrix, as judged by minimization of the `2 norm of the difference between the original matrix and the low rank approximation. However, the classical method is not resistant to corruption of individual input data points. Recently, a robust form of PCA has been proposed, in which a matrix M is decomposed as the sum of a low rank component L0 and a sparse component S0 (Candés et al., 2009):
منابع مشابه
CS 267 Final Project: A parallel incompressible two-phase flow solver for complex geometries
We present a fully 3D coupled level set projection method in arbitrary logically rectangular geometries for studying two phase immiscible incompressible flow in enclosed regions. We discuss our numerical methodology, parallelization of our algorithm, and current results.
متن کاملCS 267 Final Report Reproducible Parallel Matrix-Vector Multiply
Parallel code can be difficult to verify due to inherently non-reproducible execution models. When debugging or writing tests, users could benefit from getting the same result on different runs of the simulation. This is the goal that the ReproBLAS project (Nguyen et al.) intends to achieve. ReproBLAS [3] has so far introduced a reproducible floating point type (indexed float) and associated al...
متن کاملReProCS: A Missing Link between Recursive Robust PCA and Recursive Sparse Recovery in Large but Correlated Noise
This work studies the recursive robust principal components’ analysis (PCA) problem. Here, “robust” refers to robustness to both independent and correlated sparse outliers, although we focus on the latter. A key application where this problem occurs is in video surveillance where the goal is to separate a slowly changing background from moving foreground objects on-the-fly. The background seque...
متن کاملRelative Efficiency Measurement of Banks Using Network DEA Model in Uncertainty Situation
Traditional DEA method considered decision making units (DMUs) as a black box, regardless of their internal structure and appraisal performance with respect to the final inputs and outputs of the units. However, in many real systems we have internal structure. For this reason, network DEA models have been developed. Parallel network DEA models are a special variation which inputs of unit alloca...
متن کاملDeveloping Robust Project Scheduling Methods for Uncertain Parameters
A common problem arising in project management is the fact that the baseline schedule is often disrupted during the project execution because of uncertain parameters. As a result, project managers are often unable to meet the deadline time of the milestones. Robust project scheduling is an effective approach in case of uncertainty. Upon adopting this approach, schedules are protected against po...
متن کامل