high-dimensional data 1l1 norm 1projection operators 1singular value decomposition 1sparse data 1taxicab geometry 1
From the 1 of 3 linked papers with an AI index.
3 papers
math.FA2026
Geometric Interpretation of the Robustness of Taxicab Singular Value Decomposition of High-Dimensional Sparse Data
Vartan Choulakian
The paper compares Euclidean and Taxicab (L1) geometric interpretations of singular value decompositions, highlighting how the Taxicab SVD remains robust for extremely sparse, high…
stat.ME2025
Scale Invariant Correspondence Analysis
Vartan Choulakian
Correspondence analysis is a dimension reduction method for visualization of nonnegative data sets, in particular contingency tables ; but it depends on the marginals of the data s…
stat.AP2024
Binary Trees and Taxicab Correspondence Analysis of Extremely Sparse Binary Textual Data: A Case Study
Vartan Choulakian, Jacques Allard, Ron Kenett
This is a case study, where Taxicab Correspondence Analysis reveals that the underlying structure of an extremely sparse binary textual data set can be represented by a binary tree…