works on
composite objectives 1conditional gradient 1markovian sampling 1nonconvex optimization 1projection-free methods 1variance reduction 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

math.OC2026

Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization

Zhaojun Peng

The paper introduces a projection‑free stochastic algorithm that blends a momentum conditional‑gradient method with multilevel Monte Carlo estimation to solve nonconvex composite o…