On the accuracy of interpolation based on single-layer artificial neural networks with a focus on defeating the Runge phenomenon

• URL: http://arxiv.org/abs/2308.10720v2
• Date: Tue, 7 May 2024 17:30:50 GMT
• Title: On the accuracy of interpolation based on single-layer artificial neural networks with a focus on defeating the Runge phenomenon
• Authors: Ferdinando Auricchio, Maria Roberta Belardo, Gianluca Fabiani, Francesco Calabrò, Ariel F. Pascaner,
• Abstract summary: We consider one-hidden layer ANNs with a feedforward architecture, also referred to as shallow or two-layer networks. We present the case where the parameters are trained using a procedure that is referred to as Extreme Learning Machine (ELM) The focus is then on the accuracy of the outside of the given sampling nodes when they are thespaced, the Chebychev, and the randomly selected ones.
• Score: 29.004178992441336
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In the present paper, we consider one-hidden layer ANNs with a feedforward architecture, also referred to as shallow or two-layer networks, so that the structure is determined by the number and types of neurons. The determination of the parameters that define the function, called training, is done via the resolution of the approximation problem, so by imposing the interpolation through a set of specific nodes. We present the case where the parameters are trained using a procedure that is referred to as Extreme Learning Machine (ELM) that leads to a linear interpolation problem. In such hypotheses, the existence of an ANN interpolating function is guaranteed. The focus is then on the accuracy of the interpolation outside of the given sampling interpolation nodes when they are the equispaced, the Chebychev, and the randomly selected ones. The study is motivated by the well-known bell-shaped Runge example, which makes it clear that the construction of a global interpolating polynomial is accurate only if trained on suitably chosen nodes, ad example the Chebychev ones. In order to evaluate the behavior when growing the number of interpolation nodes, we raise the number of neurons in our network and compare it with the interpolating polynomial. We test using Runge's function and other well-known examples with different regularities. As expected, the accuracy of the approximation with a global polynomial increases only if the Chebychev nodes are considered. Instead, the error for the ANN interpolating function always decays and in most cases we observe that the convergence follows what is observed in the polynomial case on Chebychev nodes, despite the set of nodes used for training.

Related papers

• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Approximation and interpolation of deep neural networks [0.0]
  In the overparametrized regime, deep neural network provide universal approximations and can interpolate any data set. In the last section, we provide a practical probabilistic method of finding such a point under general conditions on the activation function.
  arXiv  Detail & Related papers  (2023-04-20T08:45:16Z)
• Do deep neural networks have an inbuilt Occam's razor? [1.1470070927586016]
  We show that structured data combined with an intrinsic Occam's razor-like inductive bias towards simple functions counteracts the exponential growth of functions with complexity. This analysis reveals that structured data, combined with an intrinsic Occam's razor-like inductive bias towards (Kolmogorov) simple functions that is strong enough to counteract the exponential growth of functions with complexity, is a key to the success of DNNs.
  arXiv  Detail & Related papers  (2023-04-13T16:58:21Z)
• Provable Data Subset Selection For Efficient Neural Network Training [73.34254513162898]
  We introduce the first algorithm to construct coresets for emphRBFNNs, i.e., small weighted subsets that approximate the loss of the input data on any radial basis function network. We then perform empirical evaluations on function approximation and dataset subset selection on popular network architectures and data sets.
  arXiv  Detail & Related papers  (2023-03-09T10:08:34Z)
• Push--Pull with Device Sampling [8.344476599818826]
  We consider decentralized optimization problems in which a number of agents collaborate to minimize the average of their local functions by exchanging over an underlying communication graph. We propose an algorithm that combines gradient tracking and variance reduction over the entire network. Our theoretical analysis shows that the algorithm converges linearly, when the local objective functions are strongly convex.
  arXiv  Detail & Related papers  (2022-06-08T18:18:18Z)
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks [64.92221119723048]
  Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. We propose Graph-adaptive Rectified Linear Unit (GReLU) which is a new parametric activation function incorporating the neighborhood information in a novel and efficient way. We conduct comprehensive experiments to show that our plug-and-play GReLU method is efficient and effective given different GNN backbones and various downstream tasks.
  arXiv  Detail & Related papers  (2022-02-13T10:54:59Z)
• 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)
• Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity [52.67037774136973]
  Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-ligand complexes. We propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool)
  arXiv  Detail & Related papers  (2021-07-21T03:34:09Z)
• Achieving Small Test Error in Mildly Overparameterized Neural Networks [30.664282759625948]
  We show an algorithm which finds one of these points in time. In addition, we prove that for a fully connected neural net, with an additional assumption on the data distribution, there is a time algorithm.
  arXiv  Detail & Related papers  (2021-04-24T06:47:20Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)

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.