AI RESEARCH
Mirror Descent Under Generalized Smoothness
arXiv CS.LG
•
ArXi:2502.00753v4 Announce Type: replace-cross Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the Lipschitz constant of the gradient to grow with respect to the gradient norm, which accommodates a broad range of objectives in practice.