Exact asymptotic characterisation of running time for approximate gradient descent on random graphs - LAAS-Réseaux et Communications Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Exact asymptotic characterisation of running time for approximate gradient descent on random graphs

Résumé

In this work we study the time complexity for the search of local minima in random graphs whose vertices have i.i.d. cost values. We show that, for Erd\"os-R\'enyi graphs with connection probability given by $\lambda/n^\alpha$ (with $\lambda > 0$ and $0 < \alpha < 1$), a family of local algorithms that approximate a gradient descent find local minima faster than the full gradient descent. Furthermore, we find a probabilistic representation for the running time of these algorithms leading to asymptotic estimates of the mean running times.

Dates et versions

hal-03799715 , version 1 (06-10-2022)

Identifiants

Citer

Matthieu Jonckheere, Manuel Sáenz. Exact asymptotic characterisation of running time for approximate gradient descent on random graphs. 2022. ⟨hal-03799715⟩
21 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More