Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective
This is an incremental theoretical contribution that clarifies a foundational result in neural network theory for researchers in machine learning.
The paper tackles the problem of proving that any target function can be realized near a random deep network with sufficient width, providing an elementary geometrical proof using high-dimensional geometry to simplify existing complex theories.
It is known that any target function is realized in a sufficiently small neighborhood of any randomly connected deep network, provided the width (the number of neurons in a layer) is sufficiently large. There are sophisticated theories and discussions concerning this striking fact, but rigorous theories are very complicated. We give an elementary geometrical proof by using a simple model for the purpose of elucidating its structure. We show that high-dimensional geometry plays a magical role: When we project a high-dimensional sphere of radius 1 to a low-dimensional subspace, the uniform distribution over the sphere reduces to a Gaussian distribution of negligibly small covariances.