Gradient-Variation Regret Bounds for Unconstrained Online Learning
arXiv:2604.11151v1 Announce Type: new
Abstract: We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$. For $L$…