Detecting Signs of Model Change with Continuous Model Selection Based on Descriptive Dimensionality

no code implementations • 23 Feb 2023 • Kenji Yamanishi, So Hirai

Continuous model selection is to determine the real-valued model dimensionality in terms of Ddim from a given data.

Descriptive Model Selection

Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error

no code implementations • 26 Aug 2018 • Taiji Suzuki, Hiroshi Abe, Tomoya Murata, Shingo Horiuchi, Kotaro Ito, Tokuma Wachi, So Hirai, Masatoshi Yukishima, Tomoaki Nishimura

The concept of model compression is also important for analyzing the generalization error of deep learning, known as the compression-based error bound.

Edge-computing Learning Theory +1