activity
20182026
collaborators

7 papers

cs.LG2026

Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers

Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi +1

Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems. However, they are known to be vulnerable to adversarial attacks. Countermeasure…

cs.LG2025

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…

stat.ML2025

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…

cs.IT2025

Sparse Superposition Codes with Binomial Dictionary are Capacity-Achieving with Maximum Likelihood Decoding

Yoshinari Takeishi, Jun'ichi Takeuchi

It is known that sparse superposition codes asymptotically achieve the channel capacity over the additive white Gaussian noise channel with both maximum likelihood decoding and eff…

cs.IT2024

Risk Bounds on MDL Estimators for Linear Regression Models with Application to Simple ReLU Neural Networks

Yoshinari Takeishi, Jun'ichi Takeuchi

To investigate the theoretical foundations of deep learning from the viewpoint of the minimum description length (MDL) principle, we analyse risk bounds of MDL estimators based on…

cs.LG2021

Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks

Yoshinari Takeishi, Masazumi Iida, Jun'ichi Takeuchi

We argue the Fisher information matrix (FIM) of one hidden layer networks with the ReLU activation function. For a network, let denote the weight matrix from the $…