Exact asymptotic characterisation of running time for approximate gradient descent on random graphs - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

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

(1) , (2)
1
2

Abstract

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 and versions

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

Identifiers

Cite

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

Altmetric

Share

Gmail Facebook Twitter LinkedIn More