Local complexity measures in modern parameterized function classes for supervised learning
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesColloquium Speaker: Elisenda Grigsby, Boston College Title: Local complexity measures in modern parameterized function classes for supervised learning Abstract: The parameter space for any fixed architecture of neural networks serves as a proxy during training for the associated class of functions - but how faithful is this representation? For any fixed feedforward ReLU network architecture, it […]