®®®® SIIA Público

Título del libro: Iclr 2021 - 9th International Conference On Learning Representations
Título del capítulo: MIXED-FEATURES VECTORS & SUBSPACE SPLITTING

Autores UNAM:
ALEJANDRO ESTEBAN PIMENTEL ALARCON;
Autores externos:

Idioma:

Año de publicación:
2021
Palabras clave:

Heuristic algorithms; Heuristic methods; Clusterings; Dictionary learning; Feature subspace; Features vector; Fundamental theory; Identifiability conditions; Metagenomics; Splitting algorithms; Splittings; Vector subspace; Vectors


Resumen:

Motivated by metagenomics, recommender systems, dictionary learning, and related problems, this paper introduces subspace splitting (SS): the task of clustering the entries of what we call a mixed-features vector, that is, a vector whose subsets of coordinates agree with a collection of subspaces. We derive precise identifiability conditions under which SS is well-posed, thus providing the first fundamental theory for this problem. We also propose the first three practical SS algorithms, each with advantages and disadvantages: a random sampling method, a projection-based greedy heuristic, and an alternating Lloyd-type algorithm; all allow noise, outliers, and missing data. Our extensive experiments outline the performance of our algorithms, and in lack of other SS algorithms, for reference we compare against methods for tightly related problems, like robust matched subspace detection and maximum feasible subsystem, which are special simpler cases of SS. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.


Entidades citadas de la UNAM: