A unified recursion framework for stochastic variance-reduced estimation yields high-probability bounds and the first Õ(ε^{-3}) oracle complexity for stochastic optimization with expectation constraints.
Large deviations of vector-valued martingales in 2-smooth normed spaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Exponentially-shifted Gaussian smoothing yields zeroth-order gradient estimators with linear dimension dependence, enabling improved complexity bounds for stochastic optimization including decision-dependent regimes.
citing papers explorer
-
Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
A unified recursion framework for stochastic variance-reduced estimation yields high-probability bounds and the first Õ(ε^{-3}) oracle complexity for stochastic optimization with expectation constraints.
-
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.