Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space

Abstract

We study parameter nonuniqueness in continuous-width depth-two fully connected neural networks. Our main contribution is a direct method for solving the neural-network equation $S[\gamma ]=f$. Starting from the Fourier expression of the synthesis operator, separation of variables produces a ridgelet particular solution and identifies every homogeneous direction. To isolate the argument, we first prove an abstract reconstruction formula for unitary factorizations, yielding the adjoint, normalized right inverse, and orthogonal solution geometry. We then specialize this formula to neural-network synthesis: for tempered-distribution activations such as ReLU, we equip the activation class $A_{s,t}$ with a Hilbert structure, construct compatible coefficient and parameter Hilbert spaces $H_{s,t}$ and $G_{s,t}$, and prove that $S:G_{s,t}\to L^2({\mathbb{R}}^m)$ is bounded. The resulting ridgelet expansion exhausts the null space and the complete solution set and identifies the unique minimum-norm parameter distribution. Concrete examples give adjoint ridgelet functions for standard activations. Further developments show that finite-measure null elements admit normalized width-$N$ discretizations with $O(N^{-1/2})$ output error and characterize how additive parameter perturbations can reveal information encoded in the null space. A Lean 4 blueprint for the main results is available at https://shosonoda.github.io/lean-ridgelet/ .

References in corpus (8)

• Reconciling modern machine learning practice and the bias-variance trade-off
• Benign Overfitting in Linear Regression
• Uniform convergence may be unable to explain generalization in deep learning
• Implicit Regularization in Deep Learning
• Norm-Based Capacity Control in Neural Networks
• Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network
• Width Provably Matters in Optimization for Deep Linear Neural Networks
• Universal Approximation Theorem for Equivariant Maps by Group CNNs