Stochastic AC-FGM achieves optimal O(1/√ε) iteration complexity and O(1/ε²) sample complexity while being fully adaptive to smoothness, horizon, and noise under bounded conditional variance.
In: The 22nd International Conference on Artificial Intelligence and Statistics, pp
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
-
Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates
Stochastic AC-FGM achieves optimal O(1/√ε) iteration complexity and O(1/ε²) sample complexity while being fully adaptive to smoothness, horizon, and noise under bounded conditional variance.