GloptiNets: Scalable Non-Convex Optimization with Certificates - Apprentissage de modèles visuels à partir de données massives Access content directly
Conference Papers Year : 2023

GloptiNets: Scalable Non-Convex Optimization with Certificates

Abstract

We present a novel approach to non-convex optimization with certificates, which handles smooth functions on the hypercube or on the torus. Unlike traditional methods that rely on algebraic properties, our algorithm exploits the regularity of the target function intrinsic in the decay of its Fourier spectrum. By defining a tractable family of models, we allow at the same time to obtain precise certificates and to leverage the advanced and powerful computational techniques developed to optimize neural networks. In this way the scalability of our approach is naturally enhanced by parallel computing with GPUs. Our approach, when applied to the case of polynomials of moderate dimensions but with thousands of coefficients, outperforms the state-of-the-art optimization methods with certificates, as the ones based on Lasserre's hierarchy, addressing problems intractable for the competitors.
Fichier principal
Vignette du fichier
main.pdf (428.13 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04138843 , version 1 (23-06-2023)
hal-04138843 , version 2 (04-01-2024)

Licence

Attribution

Identifiers

Cite

Gaspard Beugnot, Julien Mairal, Alessandro Rudi. GloptiNets: Scalable Non-Convex Optimization with Certificates. NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans, United States. pp.1-21. ⟨hal-04138843v2⟩
48 View
29 Download

Altmetric

Share

Gmail Facebook X LinkedIn More