arXiv Open Access 2012

Variational Optimization

Joe Staines David Barber

Lihat Sumber

Abstrak

We discuss a general technique that can be used to form a differentiable bound on the optima of non-differentiable or discrete objective functions. We form a unified description of these methods and consider under which circumstances the bound is concave. In particular we consider two concrete applications of the method, namely sparse learning and support vector classification.

Topik & Kata Kunci

stat.ML cs.LG math.NA

Penulis (2)

Joe Staines

David Barber

Format Sitasi

APA MLA BibTeX

Staines, J., Barber, D. (2012). Variational Optimization. https://arxiv.org/abs/1212.4507

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2012
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓