Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II

Abstract

We study the optimization problem associated with fitting two-layer ReLU neural networks with respect to the squared loss, where labels are generated by a target network. We make use of the rich symmetry structure to develop a novel set of tools for studying families of spurious minima. In contrast to existing approaches which operate in limiting regimes, our technique directly addresses the nonconvex loss landscape for a finite number of inputs $d$ and neurons $k$, and provides analytic, rather than heuristic, information. In particular, we derive analytic estimates for the loss at different minima, and prove that modulo $O(d^{-1/2})$-terms the Hessian spectrum concentrates near small positive constants, with the exception of $\Theta (d)$ eigenvalues which grow linearly with~$d$. We further show that the Hessian spectrum at global and spurious minima coincide to $O(d^{-1/2})$-order, thus challenging our ability to argue about statistical generalization through local curvature. Lastly, our technique provides the exact \emph{fractional} dimensionality at which families of critical points turn from saddles into spurious minima. This makes possible the study of the creation and the annihilation of spurious minima using powerful tools from equivariant bifurcation theory.

arXiv admin note: text overlap with arXiv:2008.01805

References in corpus (11)

• Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes
• Gradient Descent Happens in a Tiny Subspace
• An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
• Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
• When Do Neural Networks Outperform Kernel Methods?
• Porcupine Neural Networks: (Almost) All Local Optima are Global
• Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions
• Generalisation dynamics of online learning in over-parameterised neural networks
• Symmetry & critical points for a model shallow neural network
• On the Principle of Least Symmetry Breaking in Shallow ReLU Models
• Symmetry Breaking in Symmetric Tensor Decomposition