Phase Transition from Random Features to Fully Trainable Networks
Constructing accurate and computationally tractable approximation spaces is a fundamental task in scientific computing. Partially trainable neural networks bridge fixed random features and fully adaptive representations.
By Xin He, Huan Lao, Xiliang Lu, Shijun ZhangarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 23, 2026.
Comments
Sign in to join the discussion.