The Hybrid Momentum Stochastic Frank-Wolfe algorithm achieves O(K^{-1/4}) convergence in the generalized Frank-Wolfe gap for non-convex stochastic compositional optimization with Lipschitz outer functions.
Mathematical Programming , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
DR-MOO adds distributional robustness to multi-objective optimization and gives single-loop MGDA algorithms reaching epsilon-Pareto-stationary points in O(epsilon^{-4}) samples for nonconvex problems.
citing papers explorer
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
-
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
-
Distributionally Robust Multi-Objective Optimization
DR-MOO adds distributional robustness to multi-objective optimization and gives single-loop MGDA algorithms reaching epsilon-Pareto-stationary points in O(epsilon^{-4}) samples for nonconvex problems.