Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$

• URL: http://arxiv.org/abs/2209.08399v1
• Date: Sat, 17 Sep 2022 20:26:19 GMT
• Title: Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$
• Authors: R. Gentile, G. Welper
• Abstract summary: Two aspects of neural networks that have been extensively studied are their function approximation properties and their training by gradient descent methods. In most of the current literature these weights are fully or partially hand-crafted but not necessarily their practical performance. This paper balances these two demands and provides an approximation result for neural networks in $1d$ with non-weight optimization by gradient descent.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Two aspects of neural networks that have been extensively studied in the recent literature are their function approximation properties and their training by gradient descent methods. The approximation problem seeks accurate approximations with a minimal number of weights. In most of the current literature these weights are fully or partially hand-crafted, showing the capabilities of neural networks but not necessarily their practical performance. In contrast, optimization theory for neural networks heavily relies on an abundance of weights in over-parametrized regimes. This paper balances these two demands and provides an approximation result for shallow networks in $1d$ with non-convex weight optimization by gradient descent. We consider finite width networks and infinite sample limits, which is the typical setup in approximation theory. Technically, this problem is not over-parametrized, however, some form of redundancy reappears as a loss in approximation rate compared to best possible rates.

Related papers

• Approximation and Gradient Descent Training with Neural Networks [0.0]
  Recent work extends a neural tangent kernel (NTK) optimization argument to an under-parametrized regime. This paper establishes analogous results for networks trained by gradient descent.
  arXiv  Detail & Related papers  (2024-05-19T23:04:09Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data [63.34506218832164]
  In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with ReLU activations. For gradient flow, we leverage recent work on the implicit bias for homogeneous neural networks to show that leakyally, gradient flow produces a neural network with rank at most two. For gradient descent, provided the random variance is small enough, we show that a single step of gradient descent suffices to drastically reduce the rank of the network, and that the rank remains small throughout training.
  arXiv  Detail & Related papers  (2022-10-13T15:09:54Z)
• Slimmable Networks for Contrastive Self-supervised Learning [69.9454691873866]
  Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. We introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers. A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks.
  arXiv  Detail & Related papers  (2022-09-30T15:15:05Z)
• Stability of Deep Neural Networks via discrete rough paths [0.0]
  We provide a priori estimates for the output of Deep Residual Neural Networks in terms of both the input data and the trained network weights. We interpret residual neural network as solutions to (rough) difference equations, and analyse them based on recent results of discrete time signatures and rough path theory.
  arXiv  Detail & Related papers  (2022-01-19T12:40:28Z)
• Optimization-Based Separations for Neural Networks [57.875347246373956]
  We show that gradient descent can efficiently learn ball indicator functions using a depth 2 neural network with two layers of sigmoidal activations. This is the first optimization-based separation result where the approximation benefits of the stronger architecture provably manifest in practice.
  arXiv  Detail & Related papers  (2021-12-04T18:07:47Z)
• Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations [11.176824373696324]
  We derive the layerwise weight dynamics of infinite-width neural networks with nonlinear activations trained by gradient descent. We formulate backpropagation-free learning rules, named Align-zero and Align-ada, that theoretically achieve the same alignment as backpropagation.
  arXiv  Detail & Related papers  (2021-06-15T21:56:38Z)
• Learning Neural Network Subspaces [74.44457651546728]
  Recent observations have advanced our understanding of the neural network optimization landscape. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
  arXiv  Detail & Related papers  (2021-02-20T23:26:58Z)
• A Bayesian Perspective on Training Speed and Model Selection [51.15664724311443]
  We show that a measure of a model's training speed can be used to estimate its marginal likelihood. We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks. Our results suggest a promising new direction towards explaining why neural networks trained with gradient descent are biased towards functions that generalize well.
  arXiv  Detail & Related papers  (2020-10-27T17:56:14Z)
• Training highly effective connectivities within neural networks with randomly initialized, fixed weights [4.56877715768796]
  We introduce a novel way of training a network by flipping the signs of the weights. We obtain good results even with weights constant magnitude or even when weights are drawn from highly asymmetric distributions.
  arXiv  Detail & Related papers  (2020-06-30T09:41:18Z)

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.