Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regressionby Weigutian…
Benign Overfitting for Regression with Trained Two-Layer ReLU Networksby Junhyung Park, Patrick Bloebaum, Shiva Prasad…
On the Hardness of Learning One Hidden Layer Neural Networksby Shuchen Li, Ilias Zadik, Manolis…
Simplicity bias and optimization threshold in two-layer ReLU networksby Etienne Boursier, Nicolas FlammarionFirst submitted to…
Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networksby Ke Chen, Chugang Yi,…
Active Learning of Deep Neural Networks via Gradient-Free Cutting Planesby Erica Zhang, Fangzhao Zhang, Mert…
Nonuniform random feature models using derivative informationby Konstantin Pieper, Zezhong Zhang, Guannan ZhangFirst submitted to…
Spherical Analysis of Learning Nonlinear Functionalsby Zhenyu Yang, Shuo Huang, Han Feng, Ding-Xuan ZhouFirst submitted…
Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Studyby Hao Liu,…
Zorro: A Flexible and Differentiable Parametric Family of Activation Functions That Extends ReLU and GELUby…