Algebraic Complexity and Neurovariety of Linear Convolutional Networks

• URL: http://arxiv.org/abs/2401.16613v1
• Date: Mon, 29 Jan 2024 23:00:15 GMT
• Title: Algebraic Complexity and Neurovariety of Linear Convolutional Networks
• Authors: Vahid Shahverdi
• Abstract summary: We study linear convolutional networks with one-dimensional and arbitrary strides. We generate equations whose common zero locus corresponds to the Zariski closure of the corresponding neuromanifold. Our findings reveal that the number of all complex critical points in the optimization of such a network is equal to the generic Euclidean distance of a Segre variety.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study linear convolutional networks with one-dimensional filters and arbitrary strides. The neuromanifold of such a network is a semialgebraic set, represented by a space of polynomials admitting specific factorizations. Introducing a recursive algorithm, we generate polynomial equations whose common zero locus corresponds to the Zariski closure of the corresponding neuromanifold. Furthermore, we explore the algebraic complexity of training these networks employing tools from metric algebraic geometry. Our findings reveal that the number of all complex critical points in the optimization of such a network is equal to the generic Euclidean distance degree of a Segre variety. Notably, this count significantly surpasses the number of critical points encountered in the training of a fully connected linear network with the same number of parameters.

Related papers

• Spectral complexity of deep neural networks [2.099922236065961]
  We use the angular power spectrum of the limiting field to characterize the complexity of the network architecture. On this basis, we classify neural networks as low-disorder, sparse, or high-disorder. We show how this classification highlights a number of distinct features for standard activation functions, and in particular, sparsity properties of ReLU networks.
  arXiv  Detail & Related papers  (2024-05-15T17:55:05Z)
• Riemannian Residual Neural Networks [58.925132597945634]
  We show how to extend the residual neural network (ResNet) ResNets have become ubiquitous in machine learning due to their beneficial learning properties, excellent empirical results, and easy-to-incorporate nature when building varied neural networks.
  arXiv  Detail & Related papers  (2023-10-16T02:12:32Z)
• From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity [54.01594785269913]
  We show that optimal weights of deep ReLU neural networks are given by the wedge product of training samples when trained with standard regularized loss. The training problem reduces to convex optimization over wedge product features, which encode the geometric structure of the training dataset.
  arXiv  Detail & Related papers  (2023-09-28T15:19:30Z)
• Function Space and Critical Points of Linear Convolutional Networks [4.483341215742946]
  We study the geometry of linear networks with one-dimensional convolutional layers. We analyze the impact of the network's architecture on the function space's dimension, boundary, and singular points.
  arXiv  Detail & Related papers  (2023-04-12T10:15:17Z)
• Expressivity of Shallow and Deep Neural Networks for Polynomial Approximation [0.0]
  We establish an exponential lower bound on the complexity of any shallow network approximating the product function over a general compact domain. We also demonstrate this lower bound doesn't apply to normalized Lipschitz monomials over the unit cube.
  arXiv  Detail & Related papers  (2023-03-06T23:01:53Z)
• Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks [75.33431791218302]
  We study the training problem of deep neural networks and introduce an analytic approach to unveil hidden convexity in the optimization landscape. We consider a deep parallel ReLU network architecture, which also includes standard deep networks and ResNets as its special cases.
  arXiv  Detail & Related papers  (2021-10-18T18:00:36Z)
• 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)
• On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks Complexity [6.252236971703546]
  We introduce an equivalence relation among the linear functions composing a piecewise linear function and then count those linear functions relative to that equivalence relation. Our new complexity measure can clearly distinguish between the two models, is consistent with the classical measure, and increases exponentially with depth.
  arXiv  Detail & Related papers  (2020-10-23T01:46:12Z)
• Stability of Algebraic Neural Networks to Small Perturbations [179.55535781816343]
  Algebraic neural networks (AlgNNs) are composed of a cascade of layers each one associated to and algebraic signal model. We show how any architecture that uses a formal notion of convolution can be stable beyond particular choices of the shift operator.
  arXiv  Detail & Related papers  (2020-10-22T09:10:16Z)
• 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.