Direct high-probability last-iterate guarantee of Õ(d/T) for same-sample two-point Gaussian ZO-SGD under conditional exponential-moment noise when d ≥ 16 log(6T/δ).
arXiv preprint arXiv:2106.05958 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper motivates stochastic optimization problems from statistical perspectives and describes offline and online approaches to solve expectation minimization problems.
citing papers explorer
-
High-Probability Last-Iterate Guarantees for Two-Point Gaussian Zeroth-Order Stochastic Gradient Descent
Direct high-probability last-iterate guarantee of Õ(d/T) for same-sample two-point Gaussian ZO-SGD under conditional exponential-moment noise when d ≥ 16 log(6T/δ).
-
Stochastic Optimization and Data Science
The paper motivates stochastic optimization problems from statistical perspectives and describes offline and online approaches to solve expectation minimization problems.