MC-ALFCG attains eO((τmix^2 Gσ + τmix^{5/2} Gσ^2) ε^{-3} + τmix^5 ε^{-2}) expected sample complexity for the generalized Frank–Wolfe gap under a single ergodic Markovian stream.
Duchi, Alekh Agarwal, Mikael Johansson, and Michael I
1 Pith paper cite this work, alongside 92 external citations. Polarity classification is still indexing.
1
Pith paper citing it
92
external citations · OpenAlex
fields
math.OC 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization
MC-ALFCG attains eO((τmix^2 Gσ + τmix^{5/2} Gσ^2) ε^{-3} + τmix^5 ε^{-2}) expected sample complexity for the generalized Frank–Wolfe gap under a single ergodic Markovian stream.