Exponentially-shifted Gaussian smoothing yields zeroth-order gradient estimators with linear dimension dependence, enabling improved complexity bounds for stochastic optimization including decision-dependent regimes.
Stochastic approximation with decision- dependent distributions: asymptotic normality and optimality.Journal of Machine Learning Research, 25(90):1–49, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Complexity Guarantees for Zeroth-order Methods via Exponentially-shifted Gaussian Smoothing: Mitigating Dimension-dependence and Incorporating Decision-dependence
Exponentially-shifted Gaussian smoothing yields zeroth-order gradient estimators with linear dimension dependence, enabling improved complexity bounds for stochastic optimization including decision-dependent regimes.