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: http://creativecommons.org/licenses/by/4.0/
• 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)
• Feature Learning and Generalization in Deep Networks with Orthogonal Weights [1.7956122940209063]
  Deep neural networks with numerically weights from independent Gaussian distributions can be tuned to criticality. These networks still exhibit fluctuations that grow linearly with the depth of the network. We show analytically that rectangular networks with tanh activations and weights from the ensemble of matrices have corresponding preactivation fluctuations.
  arXiv  Detail & Related papers  (2023-10-11T18:00:02Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models [9.96121040675476]
  This manuscript explores how properties of functions learned by neural networks of depth greater than two layers affect predictions. Our framework considers a family of networks of varying depths that all have the same capacity but different representation costs.
  arXiv  Detail & Related papers  (2023-05-24T22:10:12Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• 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)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• 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)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• 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)
• Fractional moment-preserving initialization schemes for training deep neural networks [1.14219428942199]
  A traditional approach to deep neural networks (DNNs) is to sample the network weights randomly for preserving the variance of pre-activations. In this paper, we show that weights and therefore pre-activations can be modeled with a heavy-tailed distribution. We show through numerical experiments that our schemes can improve the training and test performance.
  arXiv  Detail & Related papers  (2020-05-25T01:10:01Z)
• MSE-Optimal Neural Network Initialization via Layer Fusion [68.72356718879428]
  Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. The use of gradient combined nonvolutionity renders learning susceptible to novel problems. We propose fusing neighboring layers of deeper networks that are trained with random variables.
  arXiv  Detail & Related papers  (2020-01-28T18:25:15Z)

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.