MIT proves tighter limits on step-size-scheduled gradient descent: n^-1.63 finite-horizon bound

burkov · x · 2026-09-03

Gradient descent is usually taught with a fixed step size, but recent work shows it can be sped up just by choosing step sizes in a carefully designed sequence. A new MIT CSAIL paper studies how far this idea can go on smooth convex problems:

The result gives a sharper theoretical picture of how much acceleration is possible without changing the algorithm itself.

Original post →

More from Research

Research channel →