Approximation and Learning with Deep Convolutional Models: a Kernel Perspective
arXiv:2102.10032
Abstract
The empirical success of deep convolutional networks on tasks involving high-dimensional data such as images or audio suggests that they can efficiently approximate certain functions that are well-suited for such tasks. In this paper, we study this through the lens of kernel methods, by considering simple hierarchical kernels with two or three convolution and pooling layers, inspired by convolutional kernel networks. These achieve good empirical performance on standard vision datasets, while providing a precise description of their functional space that yields new insights on their inductive bias. We show that the RKHS consists of additive models of interaction terms between patches, and that its norm encourages spatial similarities between these terms through pooling layers. We then provide generalization bounds which illustrate how pooling and patches yield improved sample complexity guarantees when the target function presents such regularities.
arXiv commentICLR 2022
References in corpus (12)
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Deep Neural Networks as Gaussian Processes
- On Exact Computation with an Infinitely Wide Neural Net
- On Lazy Training in Differentiable Programming
- Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
- Convolutional Kernel Networks
- Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
- Enhanced Convolutional Neural Tangent Kernels
- Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
- Kernel and Rich Regimes in Overparametrized Models
- Neural Kernels Without Tangents