Counting stationary points of the loss function in the simplest constrained least-square optimization

Yan V. Fyodorov; Rashel Tublin

doi:10.5506/APHYSPOLB.51.1663

Counting stationary points of the loss function in the simplest constrained least-square optimization

Yan V. Fyodorov, Rashel Tublin

Mathematics

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

We use the Kac–Rice method to analyze statistical features of an “optimization landscape” of the loss function in a random version of the Oblique Procrustes Problem, one of the simplest optimization problems of the least-square-type on a sphere.

Original language	English
Pages (from-to)	1663-1672
Number of pages	10
Journal	Acta Physica Polonica B
Volume	51
Issue number	7
DOIs	https://doi.org/10.5506/APHYSPOLB.51.1663
Publication status	Published - 2020

Access to Document

10.5506/APHYSPOLB.51.1663

Cite this

@article{9e3148ee995d4710acda6bd9f9c73faf,

title = "Counting stationary points of the loss function in the simplest constrained least-square optimization",

abstract = "We use the Kac–Rice method to analyze statistical features of an “optimization landscape” of the loss function in a random version of the Oblique Procrustes Problem, one of the simplest optimization problems of the least-square-type on a sphere.",

author = "Fyodorov, {Yan V.} and Rashel Tublin",

year = "2020",

doi = "10.5506/APHYSPOLB.51.1663",

language = "English",

volume = "51",

pages = "1663--1672",

journal = "Acta Physica Polonica B",

issn = "0587-4254",

publisher = "Jagellonian University",

number = "7",

}

TY - JOUR

T1 - Counting stationary points of the loss function in the simplest constrained least-square optimization

AU - Fyodorov, Yan V.

AU - Tublin, Rashel

PY - 2020

Y1 - 2020

N2 - We use the Kac–Rice method to analyze statistical features of an “optimization landscape” of the loss function in a random version of the Oblique Procrustes Problem, one of the simplest optimization problems of the least-square-type on a sphere.

AB - We use the Kac–Rice method to analyze statistical features of an “optimization landscape” of the loss function in a random version of the Oblique Procrustes Problem, one of the simplest optimization problems of the least-square-type on a sphere.

UR - http://www.scopus.com/inward/record.url?scp=85092720592&partnerID=8YFLogxK

U2 - 10.5506/APHYSPOLB.51.1663

DO - 10.5506/APHYSPOLB.51.1663

M3 - Article

AN - SCOPUS:85092720592

SN - 0587-4254

VL - 51

SP - 1663

EP - 1672

JO - Acta Physica Polonica B

JF - Acta Physica Polonica B

IS - 7

ER -

Counting stationary points of the loss function in the simplest constrained least-square optimization

Abstract

Access to Document

Other files and links

Fingerprint

Cite this