Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels

Abstract

We study the relative power of learning with gradient descent on differentiable models, such as neural networks, versus using the corresponding tangent kernels. We show that under certain conditions, gradient descent achieves small error only if a related tangent kernel method achieves a non-trivial advantage over random guessing (a.k.a. weak learning), though this advantage might be very small even when gradient descent can achieve arbitrarily high accuracy. Complementing this, we show that without these conditions, gradient descent can in fact learn with small error even when no kernel method, in particular using the tangent kernel, can achieve a non-trivial advantage over random guessing.

References in corpus (7)

• Gradient Descent Provably Optimizes Over-parameterized Neural Networks
• Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
• Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
• On Lazy Training in Differentiable Programming
• Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
• Learning Parities with Neural Networks
• Poly-time universality and limitations of deep learning

Cited by in corpus (4)

• What can linearized neural networks actually say about generalization?
• On Energy-Based Models with Overparametrized Shallow Neural Networks
• On the Power of Differentiable Learning versus PAC and SQ Learning
• The staircase property: How hierarchical structure can guide deep learning