Skip to content
conftrace_

finite width analysis

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hidden feature matrice (1) student-teacher network (1) network specialization (1) deep relu network (1) infinite-width limit (1) eigenvalue bound (1) relu network (1) gradient descent (1) neural network optimization (1) sample complexity (1)

Papers

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales NeurIPS 2023 Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks ICML 2021 Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension ICML 2020