Uniform Generalization Bounds for Overparameterized Neural Networks

Abstract

An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the classical statistical learning methods often result in vacuous generalization errors in the case of overparameterized neural networks. Adopting the recently developed Neural Tangent (NT) kernel theory, we prove uniform generalization bounds for overparameterized neural networks in kernel regimes, when the true data generating model belongs to the reproducing kernel Hilbert space (RKHS) corresponding to the NT kernel. Importantly, our bounds capture the exact error rates depending on the differentiability of the activation functions. In order to establish these bounds, we propose the information gain of the NT kernel as a measure of complexity of the learning problem. Our analysis uses a Mercer decomposition of the NT kernel in the basis of spherical harmonics and the decay rate of the corresponding eigenvalues. As a byproduct of our results, we show the equivalence between the RKHS corresponding to the NT kernel and its counterpart corresponding to the Matérn family of kernels, showing the NT kernels induce a very general class of models. We further discuss the implications of our analysis for some recent results on the regret bounds for reinforcement learning and bandit algorithms, which use overparameterized neural networks.

References in corpus (16)

• Language Models are Few-Shot Learners
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• On Lazy Training in Differentiable Programming
• Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
• Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
• Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
• Finite-Time Analysis of Kernelised Contextual Bandits
• The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
• Neural Contextual Bandits with UCB-based Exploration
• Matérn Gaussian processes on Riemannian manifolds
• Sparse Gaussian Processes with Spherical Harmonic Features
• Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network
• Deep Equals Shallow for ReLU Networks in Kernel Regimes
• Optimal Order Simple Regret for Gaussian Process Bandits
• A Short Note on the Relationship of Information Gain and Eluder Dimension
• Open Problem: Tight Online Confidence Intervals for RKHS Elements