3 papers
cs.LG2025
Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
Hyungu Lee, Taehyeong Kim, Hayoung Choi
Stable and efficient training of ReLU networks with large depth is highly sensitive to weight initialization. Improper initialization can cause permanent neuron inactivation dying…
math.AC2023
Finding tensor decompositions with sparse optimization
Taehyeong Kim, Jeong-Hoon Ju, Yeongrak Kim
In this paper, we suggest a new method for a given tensor to find CP decompositions using a less number of rank tensors. The main ingredient is the Least Absolute Shrinkage and…
math.AC2023
A new formula of the determinant tensor with symmetries
Jeong-Hoon Ju, Taehyeong Kim, Yeongrak Kim
In this paper, we present a new formula of the determinant tensor for matrices. In \cite{kim2023newdet4}, Kim, Ju, and Kim found a new formula of …