AI RESEARCH
Step-Size Decay and Structural Stagnation in Greedy Sparse Learning
arXiv CS.LG
•
ArXi:2603.07703v1 Announce Type: new Greedy algorithms are central to sparse approximation and stage-wise learning methods such as matching pursuit and boosting. It is known that the Power-Relaxed Greedy Algorithm with step sizes $m^{-\alpha}$ may fail to converge when $\alpha>1$ in general Hilbert spaces. In this work, we revisit this phenomenon from a sparse learning perspective.