Publications
Effects of width-dependent model hyperparameters and $\ell_2$-regularization on the loss landscape of two-layer ReLU networks (ICML 2026 4th Workshop on High-dimensional Learning Dynamics) link.
Effects of width-dependent model hyperparameters and $\ell_2$-regularization on the loss landscape of two-layer ReLU networks (ICML 2026 4th Workshop on High-dimensional Learning Dynamics) link.