Showing math.OCShow all
2 papers · 1 filter
math.OC2026
Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent
Jason M. Altschuler, Pablo A. Parrilo
Can gradient descent be accelerated by just choosing better stepsizes? Surprisingly, the answer is yes. This short expository article provides an accessible introduction to this ph…
math.OC2026
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…