Abstract | ||
---|---|---|
Archetypal analysis and nonnegative matrix factorization (NMF) are staples in a statistician's toolbox for dimension reduction and exploratory data analysis. We describe a geometric approach to both NMF and archetypal analysis by interpreting both problems as finding extreme points of the data cloud. We also develop and analyze an efficient approach to finding extreme points in high dimensions. For modern massive datasets that are too large to fit on a single machine and must be stored in a distributed setting, our approach makes only a small number of passes over the data. In fact, it is possible to obtain the NMF or perform archetypal analysis with just two passes over the data. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1080/00401706.2016.1247017 | TECHNOMETRICS |
Keywords | Field | DocType |
Convex hull,Group lasso,Random projections | Extreme point,Small number,Dimensionality reduction,Toolbox,Convex hull,Non-negative matrix factorization,Exploratory data analysis,Statistics,Mathematics,Cloud computing | Journal |
Volume | Issue | ISSN |
59.0 | 3.0 | 0040-1706 |
Citations | PageRank | References |
1 | 0.37 | 12 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anil Damle | 1 | 21 | 6.13 |
Yuekai Sun | 2 | 1 | 0.37 |