Over-parametrized neural networks as under-determined linear systems

• URL: http://arxiv.org/abs/2010.15959v1
• Date: Thu, 29 Oct 2020 21:43:00 GMT
• Title: Over-parametrized neural networks as under-determined linear systems
• Authors: Austin R. Benson, Anil Damle, Alex Townsend
• Abstract summary: We show that it is unsurprising simple neural networks can achieve zero training loss. We show that kernels typically associated with the ReLU activation function have fundamental flaws. We propose new activation functions that avoid the pitfalls of ReLU in that they admit zero training loss solutions for any set of distinct data points.
• Score: 31.69089186688224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising such networks can achieve zero training loss. More specifically, we provide lower bounds on the width of a single hidden layer neural network such that only training the last linear layer suffices to reach zero training loss. Our lower bounds grow more slowly with data set size than existing work that trains the hidden layer weights. Second, we show that kernels typically associated with the ReLU activation function have fundamental flaws -- there are simple data sets where it is impossible for widely studied bias-free models to achieve zero training loss irrespective of how the parameters are chosen or trained. Lastly, our analysis of gradient descent clearly illustrates how spectral properties of certain matrices impact both the early iteration and long-term training behavior. We propose new activation functions that avoid the pitfalls of ReLU in that they admit zero training loss solutions for any set of distinct data points and experimentally exhibit favorable spectral properties.

Related papers

• Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse [32.06666853127924]
  Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a symmetric geometric structure referred to as neural collapse. Here, the features of the penultimate layer are free variables, which makes the model data-agnostic and, hence, puts into question its ability to capture training. We first prove generic guarantees on neural collapse that assume (i) low training error and balancedness of the linear layers, and (ii) bounded conditioning of the features before the linear part.
  arXiv  Detail & Related papers  (2024-10-07T10:16:40Z)
• Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs [5.7166378791349315]
  We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network converges to zero loss. We also show and characterise a surprising distinction in this setting between interpolator networks of minimal rank and those of minimal Euclidean norm.
  arXiv  Detail & Related papers  (2023-06-10T16:36:22Z)
• Benign Overfitting for Two-layer ReLU Convolutional Neural Networks [60.19739010031304]
  We establish algorithm-dependent risk bounds for learning two-layer ReLU convolutional neural networks with label-flipping noise. We show that, under mild conditions, the neural network trained by gradient descent can achieve near-zero training loss and Bayes optimal test risk.
  arXiv  Detail & Related papers  (2023-03-07T18:59:38Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• 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)
• Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data [44.431266188350655]
  We consider the generalization error of two-layer neural networks trained to generalize by gradient descent. We show that neural networks exhibit benign overfitting: they can be driven to zero training error, perfectly fitting any noisy training labels, and simultaneously achieve minimax optimal test error. In contrast to previous work on benign overfitting that require linear or kernel-based predictors, our analysis holds in a setting where both the model and learning dynamics are fundamentally nonlinear.
  arXiv  Detail & Related papers  (2022-02-11T23:04:00Z)
• Training invariances and the low-rank phenomenon: beyond linear networks [44.02161831977037]
  We show that when one trains a deep linear network with logistic or exponential loss on linearly separable data, the weights converge to rank-$1$ matrices. This is the first time a low-rank phenomenon is proven rigorously for nonlinear ReLU-activated feedforward networks. Our proof relies on a specific decomposition of the network into a multilinear function and another ReLU network whose weights are constant under a certain parameter directional convergence.
  arXiv  Detail & Related papers  (2022-01-28T07:31:19Z)
• 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)
• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks [80.55378250013496]
  We study how neural networks trained by gradient descent extrapolate what they learn outside the support of the training distribution. Graph Neural Networks (GNNs) have shown some success in more complex tasks.
  arXiv  Detail & Related papers  (2020-09-24T17:48:59Z)
• The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks [43.860358308049044]
  In work, we show that these common perceptions can be completely false in the early phase of learning. We argue that this surprising simplicity can persist in networks with more layers with convolutional architecture.
  arXiv  Detail & Related papers  (2020-06-25T17:42:49Z)
• Feature Purification: How Adversarial Training Performs Robust Deep Learning [66.05472746340142]
  We show a principle that we call Feature Purification, where we show one of the causes of the existence of adversarial examples is the accumulation of certain small dense mixtures in the hidden weights during the training process of a neural network. We present both experiments on the CIFAR-10 dataset to illustrate this principle, and a theoretical result proving that for certain natural classification tasks, training a two-layer neural network with ReLU activation using randomly gradient descent indeed this principle.
  arXiv  Detail & Related papers  (2020-05-20T16:56:08Z)

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.