Momentum SGD incurs a provable drift-amplification penalty in nonstationary stochastic optimization that makes it worse than vanilla SGD in drift-dominated regimes, confirmed by finite-time upper bounds and minimax lower bounds under gradient-variation constraints.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.
citing papers explorer
-
On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
Momentum SGD incurs a provable drift-amplification penalty in nonstationary stochastic optimization that makes it worse than vanilla SGD in drift-dominated regimes, confirmed by finite-time upper bounds and minimax lower bounds under gradient-variation constraints.
-
Inherited or produced? Inferring protein production kinetics when protein counts are shaped by a cell's division history
Conditional normalizing flows approximate intractable likelihoods arising from cell division history to conclude that glc3 is mostly inactive under nutrient stress in yeast, with brief transient expression.