Asymptotics of Learning with Deep Structured (Random) Features
- URL: http://arxiv.org/abs/2402.13999v2
- Date: Mon, 10 Jun 2024 10:16:19 GMT
- Title: Asymptotics of Learning with Deep Structured (Random) Features
- Authors: Dominik Schröder, Daniil Dmitriev, Hugo Cui, Bruno Loureiro,
- Abstract summary: For a large class of feature maps we provide a tight characterisation of the test error associated with learning the readout layer.
In some cases our results can capture feature maps learned by deep, finite-width neural networks trained under gradient descent.
- Score: 9.366617422860543
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where the input dimension, hidden layer widths, and number of training samples are proportionally large. This characterization is formulated in terms of the population covariance of the features. Our work is partially motivated by the problem of learning with Gaussian rainbow neural networks, namely deep non-linear fully-connected networks with random but structured weights, whose row-wise covariances are further allowed to depend on the weights of previous layers. For such networks we also derive a closed-form formula for the feature covariance in terms of the weight matrices. We further find that in some cases our results can capture feature maps learned by deep, finite-width neural networks trained under gradient descent.
Related papers
- Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers [39.71511919246829]
Deep linear networks have been extensively studied, but little is known in the case of finite-width architectures with multiple outputs and convolutional layers.
Our work provides a dictionary that translates this physics intuition and terminology into rigorous Bayesian statistics.
arXiv Detail & Related papers (2024-06-05T13:37:42Z) - Wide Neural Networks as Gaussian Processes: Lessons from Deep
Equilibrium Models [16.07760622196666]
We study the deep equilibrium model (DEQ), an infinite-depth neural network with shared weight matrices across layers.
Our analysis reveals that as the width of DEQ layers approaches infinity, it converges to a Gaussian process.
Remarkably, this convergence holds even when the limits of depth and width are interchanged.
arXiv Detail & Related papers (2023-10-16T19:00:43Z) - From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity [54.01594785269913]
We show that optimal weights of deep ReLU neural networks are given by the wedge product of training samples when trained with standard regularized loss.
The training problem reduces to convex optimization over wedge product features, which encode the geometric structure of the training dataset.
arXiv Detail & Related papers (2023-09-28T15:19:30Z) - Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence.
We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers.
This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
arXiv Detail & Related papers (2023-07-20T13:34:11Z) - Bayesian Interpolation with Deep Linear Networks [92.1721532941863]
Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory.
We show that linear networks make provably optimal predictions at infinite depth.
We also show that with data-agnostic priors, Bayesian model evidence in wide linear networks is maximized at infinite depth.
arXiv Detail & Related papers (2022-12-29T20:57:46Z) - The Separation Capacity of Random Neural Networks [78.25060223808936]
We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability.
We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
arXiv Detail & Related papers (2021-07-31T10:25:26Z) - Deep Networks Provably Classify Data on Curves [12.309532551321334]
We study a model problem that uses a deep fully-connected neural network to classify data drawn from two disjoint smooth curves on the unit sphere.
We prove that when (i) the network depth is large to certain properties that set the difficulty of the problem and (ii) the network width and number of samples is intrinsic in the relative depth, randomly-d gradient descent quickly learns to correctly classify all points on the two curves with high probability.
arXiv Detail & Related papers (2021-07-29T20:40:04Z) - Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
We propose a topological perspective to represent a network into a complete graph for analysis.
By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner.
This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
arXiv Detail & Related papers (2020-08-19T04:53:31Z) - Beyond Dropout: Feature Map Distortion to Regularize Deep Neural
Networks [107.77595511218429]
In this paper, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks.
We propose a feature distortion method (Disout) for addressing the aforementioned problem.
The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated.
arXiv Detail & Related papers (2020-02-23T13:59:13Z) - Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations [2.3018169548556977]
We study the effects of Rectified Linear Units on the capacity and on the geometrical landscape of the solution space in two-layer neural networks.
We find that, quite unexpectedly, the capacity of the network remains finite as the number of neurons in the hidden layer increases.
Possibly more important, a large deviation approach allows us to find that the geometrical landscape of the solution space has a peculiar structure.
arXiv Detail & Related papers (2019-07-17T15:23:17Z)
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.