arXiv Open Access 2015

Dictionary descent in optimization

Vladimir Temlyakov

Lihat Sumber

Abstrak

The problem of convex optimization is studied. Usually in convex optimization the minimization is over a d-dimensional domain. Very often the convergence rate of an optimization algorithm depends on the dimension d. The algorithms studied in this paper utilize dictionaries instead of a canonical basis used in the coordinate descent algorithms. We show how this approach allows us to reduce dimensionality of the problem. Also, we investigate which properties of a dictionary are beneficial for the convergence rate of typical greedy-type algorithms.

Topik & Kata Kunci

stat.ML math.NA

Penulis (1)

Vladimir Temlyakov

Format Sitasi

APA MLA BibTeX

Temlyakov, V. (2015). Dictionary descent in optimization. https://arxiv.org/abs/1511.01304

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2015
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓