Establishes that no positive stepsize schedule achieves better than o(n^{-1.334}) anytime convergence for function values or o(n^{-1}) for squared gradient norms in smooth convex optimization.
Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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 phenomenon of stepsize hedging.
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lower Bounds for Anytime Acceleration of Gradient Descent
Establishes that no positive stepsize schedule achieves better than o(n^{-1.334}) anytime convergence for function values or o(n^{-1}) for squared gradient norms in smooth convex optimization.