3 papers
math.OC2026
Restart and Adaptive Acceleration in Stochastic Gradient Methods
Ali Elhishi, Chistophe Roux, Alexandre d'Aspremont
We study restart schemes in stochastic optimization problems for non-smooth and weakly convex functions that satisfy a Kurdyka-Łojasiewicz (KŁ) inequality. Using restarts allows us…
math.OC2017
Sharpness, Restart and Acceleration
Vincent Roulet, Alexandre d'Aspremont
The Łojasiewicz inequality shows that sharpness bounds on the minimum of convex optimization problems hold almost generically. Sharpness directly controls the performance of restar…
math.OC2015
Computational Complexity versus Statistical Performance on Sparse Recovery Problems
Vincent Roulet, Nicolas Boumal, Alexandre d'Aspremont
We show that several classical quantities controlling compressed sensing performance directly match classical parameters controlling algorithmic complexity. We first describe linea…