290 citations · 492 across the 36 of their papers we have counts for
Showing 2024 · math.OCShow all
2 papers · 2 filters
math.OC2024
Acceleration by Random Stepsizes: Hedging, Equalization, and the Arcsine Stepsize Schedule
Jason M. Altschuler, Pablo A. Parrilo
We show that for separable convex optimization, random stepsizes fully accelerate Gradient Descent. Specifically, using inverse stepsizes i.i.d. from the Arcsine distribution impro…
math.OC2024
Accelerating Proximal Gradient Descent via Silver Stepsizes
Jinho Bok, Jason M. Altschuler
Surprisingly, recent work has shown that gradient descent can be accelerated without using momentum -- just by judiciously choosing stepsizes. An open question raised by several pa…