"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

1 code implementation • 1 Mar 2024 • Lingyu Gu, Yongqi Du, Yuan Zhang, Di Xie, ShiLiang Pu, Robert C. Qiu, Zhenyu Liao

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging.

Model Compression Quantization