2022
DOI: 10.20537/2076-7633-2022-14-2-277-308
|View full text |Cite
|
Sign up to set email alerts
|

Averaged heavy-ball method

Abstract: Методы оптимизации первого порядка являются важным рабочим инструментов для широкого спектра современных приложений в разных областях, среди которых можно выделить экономику, физику, биологию, машинное обучение и управление. Среди методов первого порядка особого внимания заслуживают ускоренные (моментные) методы в силу их практической эффективности. Метод тяжелого шарика (heavy-ball method -HB) -один из первых ускоренных методов. Данный метод был разработан в 1964 г., и для него был проведен анализ сходимости … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(5 citation statements)
references
References 10 publications
(5 reference statements)
0
5
0
Order By: Relevance
“…Positive values of φ ′ 1 (λ) can be realized when the following inequality is valid: (15). Let us demonstrate that (16) correlates with (14): Inequity (16)…”
Section: And In This Casementioning
confidence: 90%
See 2 more Smart Citations
“…Positive values of φ ′ 1 (λ) can be realized when the following inequality is valid: (15). Let us demonstrate that (16) correlates with (14): Inequity (16)…”
Section: And In This Casementioning
confidence: 90%
“…The opposite inequality guarantees that it is valid for all λ > 0. For analysis of the general situation of the sign of D this restriction is too strict, so we consider the case of condition (14). The case of D < 0 leads to the investigation of function…”
Section: And In This Casementioning
confidence: 99%
See 1 more Smart Citation
“…As we will show later in Lemma 6, the gradient norm of averaged solutions is small, which leads to stability. For strongly-convex quadratic problems, Danilova and Malinovsky [16] also show that averaged HB methods have a smaller maximal deviation from the optimal solution than the vanilla HB method. A similar effect for nonconvex problems is expected in the neighborhood of local optima where quadratic approximation is justified.…”
Section: Restart Mechanismsmentioning
confidence: 96%
“…for all k ≥ 1. Our choice of θ k differs from the existing ones; the existing complexity analyses [16,17,21,32,34,43] of HB prohibit θ k = 1. For example, Li and Lin [34] proposed…”
Section: Update Of Solutionsmentioning
confidence: 99%