Nesterov and heavy-ball acceleration are extended to probability-measure optimization through dual lifting, with claimed non-asymptotic rates matching the Euclidean case.
From Optimization to Sampling Through Gradient Flows
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Nesterov acceleration in optimizing over probability measures
Nesterov and heavy-ball acceleration are extended to probability-measure optimization through dual lifting, with claimed non-asymptotic rates matching the Euclidean case.