Almost surely constrained convex optimization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Almost surely constrained convex optimization

Résumé

We propose a stochastic gradient framework for solving stochastic composite convex optimization problems with (possibly) infinite number of linear inclusion constraints that need to be satisfied almost surely. We use smoothing and homotopy techniques to handle constraints without the need for matrix-valued projections. We show for our stochastic gradient algorithm $\mathcal{O}(\log(k)/\sqrt{k})$ convergence rate for general convex objectives and $\mathcal{O}(\log(k)/k)$ convergence rate for restricted strongly convex objectives. These rates are known to be optimal up to logarithmic factors, even without constraints. We demonstrate the performance of our algorithm with numerical experiments on basis pursuit, a hard margin support vector machines and a portfolio optimization and show that our algorithm achieves state-of-the-art practical performance.

Dates et versions

hal-02007623 , version 1 (05-02-2019)

Identifiants

Citer

Olivier Fercoq, Ahmet Alacaoglu, Ion Necoara, Volkan Cevher. Almost surely constrained convex optimization. International Conference on Machine Learning, 2019, Long Beach, United States. pp.1910-1919. ⟨hal-02007623⟩
46 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More