4 papers
Approximating Simple ReLU Networks based on Spectral Decomposition of Fisher Information
Ka Long Keith Ho, Yoshinari Takeishi, Junichi Takeuchi
Properties of Fisher information matrices of 2-layer neural ReLU networks with random hidden weights are studied. For these networks, it is known that the eigenvalue distribution h…
Neural Tangent Kernels and Fisher Information Matrices for Simple ReLU Networks with Random Hidden Weights
Jun'ichi Takeuchi, Yoshinari Takeishi, Noboru Murata +3
Fisher information matrices and neural tangent kernels (NTK) for 2-layer ReLU networks with random hidden weight are argued. We discuss the relation between both notions as a linea…
Variable selection via thresholding
Ka Long Keith Ho, Hien Duy Nguyen
Variable selection comprises an important step in many modern statistical inference procedures. In the regression setting, when estimators cannot shrink irrelevant signals to zero,…
Adaptive Ridge Approach to Heteroscedastic Regression
Ka Long Keith Ho, Hiroki Masuda
We propose an adaptive ridge (AR) estimation scheme for a heteroscedastic linear regression model with log-linear noise in data. We simultaneously estimate the mean and variance pa…