AI RESEARCH
Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses
arXiv CS.LG
•
ArXi:2605.10219v1 Announce Type: cross We study the parameterized complexity of testing approximate first-order stationarity at a prescribed point for continuous piecewise-affine (PA) functions, a basic task in nonsmooth optimization. PA functions form a canonical model for nonsmooth stationarity testing and capture the local polyhedral geometry that appears in ReLU-type