Double-descent curves in neural networks: a new perspective using Gaussian processes

• URL: http://arxiv.org/abs/2102.07238v5
• Date: Thu, 25 May 2023 19:08:48 GMT
• Title: Double-descent curves in neural networks: a new perspective using Gaussian processes
• Authors: Ouns El Harzli, Bernardo Cuenca Grau, Guillermo Valle-P\'erez and Ard A. Louis
• Abstract summary: Double-descent curves in neural networks describe the phenomenon that the generalisation error initially descends with increasing parameters, then grows after reaching an optimal number of parameters. We use techniques from random matrix theory to characterize the spectral distribution of the empirical feature covariance matrix as a width-dependent of the spectrum of the neural network Gaussian process kernel.
• Score: 9.153116600213641
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Double-descent curves in neural networks describe the phenomenon that the generalisation error initially descends with increasing parameters, then grows after reaching an optimal number of parameters which is less than the number of data points, but then descends again in the overparameterized regime. In this paper, we use techniques from random matrix theory to characterize the spectral distribution of the empirical feature covariance matrix as a width-dependent perturbation of the spectrum of the neural network Gaussian process (NNGP) kernel, thus establishing a novel connection between the NNGP literature and the random matrix theory literature in the context of neural networks. Our analytical expression allows us to study the generalisation behavior of the corresponding kernel and GP regression, and provides a new interpretation of the double-descent phenomenon, namely as governed by the discrepancy between the width-dependent empirical kernel and the width-independent NNGP kernel.

Related papers

• Sparse deep neural networks for nonparametric estimation in high-dimensional sparse regression [4.983567824636051]
  This study combines nonparametric estimation and parametric sparse deep neural networks for the first time. As nonparametric estimation of partial derivatives is of great significance for nonlinear variable selection, the current results show the promising future for the interpretability of deep neural networks.
  arXiv  Detail & Related papers  (2024-06-26T07:41:41Z)
• Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime [52.00917519626559]
  This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology. We also present an exact novel representor theory for layer-wise neural network training with unregularized gradient descent in terms of a local-extrinsic neural kernel (LeNK) This representor theory gives insight into the role of higher-order statistics in neural network training and the effect of kernel evolution in neural-network kernel models.
  arXiv  Detail & Related papers  (2024-05-24T06:30:36Z)
• Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs [94.44374472696272]
  We investigate NTKs and alignment in the context of graph neural networks (GNNs) Our results establish the theoretical guarantees on the optimality of the alignment for a two-layer GNN. These guarantees are characterized by the graph shift operator being a function of the cross-covariance between the input and the output data.
  arXiv  Detail & Related papers  (2023-10-16T19:54:21Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Interrelation of equivariant Gaussian processes and convolutional neural networks [77.34726150561087]
  Currently there exists rather promising new trend in machine leaning (ML) based on the relationship between neural networks (NN) and Gaussian processes (GP) In this work we establish a relationship between the many-channel limit for CNNs equivariant with respect to two-dimensional Euclidean group with vector-valued neuron activations and the corresponding independently introduced equivariant Gaussian processes (GP)
  arXiv  Detail & Related papers  (2022-09-17T17:02:35Z)
• Phenomenology of Double Descent in Finite-Width Neural Networks [29.119232922018732]
  Double descent delineates the behaviour of models depending on the regime they belong to. We use influence functions to derive suitable expressions of the population loss and its lower bound. Building on our analysis, we investigate how the loss function affects double descent.
  arXiv  Detail & Related papers  (2022-03-14T17:39:49Z)
• Uniform Generalization Bounds for Overparameterized Neural Networks [5.945320097465419]
  We prove uniform generalization bounds for overparameterized neural networks in kernel regimes. Our bounds capture the exact error rates depending on the differentiability of the activation functions. We show the equivalence between the RKHS corresponding to the NT kernel and its counterpart corresponding to the Mat'ern family of kernels.
  arXiv  Detail & Related papers  (2021-09-13T16:20:13Z)
• Linear approximability of two-layer neural networks: A comprehensive analysis based on spectral decay [4.042159113348107]
  We first consider the case of single neuron and show that the linear approximability, quantified by the Kolmogorov width, is controlled by the eigenvalue decay of an associate kernel. We show that similar results also hold for two-layer neural networks.
  arXiv  Detail & Related papers  (2021-08-10T23:30:29Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks [17.188280334580195]
  We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples. Our expressions apply to wide neural networks due to an equivalence between training them and kernel regression with the Neural Kernel Tangent (NTK) We verify our theory with simulations on synthetic data and MNIST dataset.
  arXiv  Detail & Related papers  (2020-02-07T00:03:40Z)
• On the Convex Behavior of Deep Neural Networks in Relation to the Layers' Width [99.24399270311069]
  We observe that for wider networks, minimizing the loss with the descent optimization maneuvers through surfaces of positive curvatures at the start and end of training, and close to zero curvatures in between. In other words, it seems that during crucial parts of the training process, the Hessian in wide networks is dominated by the component G.
  arXiv  Detail & Related papers  (2020-01-14T16:30:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.