Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks

Abstract

We study the sample complexity of learning one-hidden-layer convolutional neural networks (CNNs) with non-overlapping filters. We propose a novel algorithm called approximate gradient descent for training CNNs, and show that, with high probability, the proposed algorithm with random initialization grants a linear convergence to the ground-truth parameters up to statistical precision. Compared with existing work, our result applies to general non-trivial, monotonic and Lipschitz continuous activation functions including ReLU, Leaky ReLU, Sigmod and Softplus etc. Moreover, our sample complexity beats existing results in the dependency of the number of hidden nodes and filter size. In fact, our result matches the information-theoretic lower bound for learning one-hidden-layer CNNs with linear activation functions, suggesting that our sample complexity is tight. Our theoretical analysis is backed up by numerical experiments.

45 pages, 3 figures, 1 table. In NeurIPS 2019

Cited by in corpus (7)

• Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks
• A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
• Agnostic Learning of a Single Neuron with Gradient Descent
• Directional Pruning of Deep Neural Networks
• Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical Systems
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
• Learning Graph Neural Networks with Approximate Gradient Descent