Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

• URL: http://arxiv.org/abs/2311.18022v4
• Date: Sun, 06 Oct 2024 22:24:07 GMT
• Title: Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
• Authors: Max Milkert, David Hyde, Forrest Laine,
• Abstract summary: A neural network with ReLU activations may be viewed as a composition of piecewise linear functions. We introduce a novel training strategy that forces the network to exhibit a number of linear regions exponential in depth. This approach allows us to learn approximations of convex, one-dimensional functions that are several orders of magnitude more accurate than their randomly counterparts.
• Score: 1.7205106391379021
• License:
• Abstract: A neural network with ReLU activations may be viewed as a composition of piecewise linear functions. For such networks, the number of distinct linear regions expressed over the input domain has the potential to scale exponentially with depth, but it is not expected to do so when the initial parameters are chosen randomly. Therefore, randomly initialized models are often unnecessarily large, even when approximating simple functions. To address this issue, we introduce a novel training strategy: we first reparameterize the network weights in a manner that forces the network to exhibit a number of linear regions exponential in depth. Training first on our derived parameters provides an initial solution that can later be refined by directly updating the underlying model weights. This approach allows us to learn approximations of convex, one-dimensional functions that are several orders of magnitude more accurate than their randomly initialized counterparts. We further demonstrate how to extend our approach to multidimensional and non convex functions, with similar benefits observed.

Related papers

• Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks [0.5827521884806072]
  Large neural networks trained on large datasets have become the dominant paradigm in machine learning. This thesis develops scalable methods to equip neural networks with model uncertainty.
  arXiv  Detail & Related papers  (2024-04-29T23:38:58Z)
• The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models [75.33431791218302]
  Deep Neural Network Network (DNN) models are used for programming purposes. In this paper we examine the use of convex neural recovery models. We show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program. We also show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program.
  arXiv  Detail & Related papers  (2023-12-19T23:04:56Z)
• 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)
• Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth [92.25666446274188]
  sinusoidal neural networks with activations have been proposed as an alternative to networks with traditional activation functions. We first propose a simplified version of such sinusoidal neural networks, which allows both for easier practical implementation and simpler theoretical analysis. We then analyze the behavior of these networks from the neural tangent kernel perspective and demonstrate that their kernel approximates a low-pass filter with an adjustable bandwidth.
  arXiv  Detail & Related papers  (2022-11-26T07:41:48Z)
• Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable [1.2277343096128712]
  Given sufficient width, a randomly one-layer neural network can transform two sets into two linearly separable sets without any training. This paper contributes by establishing that, given sufficient width, a randomly one-layer neural network can transform two sets into two linearly separable sets without any training.
  arXiv  Detail & Related papers  (2022-05-24T01:38:43Z)
• Subquadratic Overparameterization for Shallow Neural Networks [60.721751363271146]
  We provide an analytical framework that allows us to adopt standard neural training strategies. We achieve the desiderata viaak-Lojasiewicz, smoothness, and standard assumptions.
  arXiv  Detail & Related papers  (2021-11-02T20:24:01Z)
• Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit [0.0]
  Large-width dynamics has emerged as a fruitful viewpoint and led to practical insights on real-world deep networks. For two-layer neural networks, it has been understood that the nature of the trained model radically changes depending on the scale of the initial random weights. We propose various methods to avoid this trivial behavior and analyze in detail the resulting dynamics.
  arXiv  Detail & Related papers  (2021-10-29T07:53:35Z)
• Activation function design for deep networks: linearity and effective initialisation [10.108857371774977]
  We study how to avoid two problems at initialisation identified in prior works. We prove that both these problems can be avoided by choosing an activation function possessing a sufficiently large linear region around the origin.
  arXiv  Detail & Related papers  (2021-05-17T11:30:46Z)
• On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks [1.0323063834827415]
  We present a novel analysis of single-hidden-layer linear networks trained under gradient flow. We show that the squared loss converges exponentially to its optimum. We derive a novel non-asymptotic upper-bound on the distance between the trained network and the min-norm solution.
  arXiv  Detail & Related papers  (2021-05-13T15:13:51Z)
• On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent [55.96478231566129]
  We show that relative scales play an important role in determining the learned model. We develop a technique for deriving the inductive bias of gradient-flow.
  arXiv  Detail & Related papers  (2021-02-19T07:10:48Z)
• Measuring Model Complexity of Neural Networks with Curve Activation Functions [100.98319505253797]
  We propose the linear approximation neural network (LANN) to approximate a given deep model with curve activation function. We experimentally explore the training process of neural networks and detect overfitting. We find that the $L1$ and $L2$ regularizations suppress the increase of model complexity.
  arXiv  Detail & Related papers  (2020-06-16T07:38:06Z)

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.