Universal approximation property of invertible neural networks

• URL: http://arxiv.org/abs/2204.07415v1
• Date: Fri, 15 Apr 2022 10:45:26 GMT
• Title: Universal approximation property of invertible neural networks
• Authors: Isao Ishikawa, Takeshi Teshima, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama
• Abstract summary: Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various machine learning applications such as probabilistic modeling, generative modeling, and representation learning.
• Score: 76.95927093274392
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various machine learning applications such as probabilistic modeling, generative modeling, and representation learning. However, their attractive properties often come at the cost of restricting the layer designs, which poses a question on their representation power: can we use these models to approximate sufficiently diverse functions? To answer this question, we have developed a general theoretical framework to investigate the representation power of INNs, building on a structure theorem of differential geometry. The framework simplifies the approximation problem of diffeomorphisms, which enables us to show the universal approximation properties of INNs. We apply the framework to two representative classes of INNs, namely Coupling-Flow-based INNs (CF-INNs) and Neural Ordinary Differential Equations (NODEs), and elucidate their high representation power despite the restrictions on their architectures.

Related papers

• E(n) Equivariant Topological Neural Networks [10.603892843083173]
  Graph neural networks excel at modeling pairwise interactions, but they cannot flexibly accommodate higher-order interactions and features. Topological deep learning (TDL) has emerged recently as a promising tool for addressing this issue. This paper introduces E(n)-Equivariant Topological Neural Networks (ETNNs) ETNNs incorporate geometric node features while respecting rotation, reflection, and translation.
  arXiv  Detail & Related papers  (2024-05-24T10:55:38Z)
• An Algorithm to Train Unrestricted Sequential Discrete Morphological Neural Networks [0.0]
  We propose an algorithm to learn unrestricted sequential DMNN, whose architecture is given by the composition of general W-operators. We illustrate the algorithm in a practical example.
  arXiv  Detail & Related papers  (2023-10-06T20:55:05Z)
• Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study [55.12108376616355]
  The study on NTK has been devoted to typical neural network architectures, but is incomplete for neural networks with Hadamard products (NNs-Hp) In this work, we derive the finite-width-K formulation for a special class of NNs-Hp, i.e., neural networks. We prove their equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK.
  arXiv  Detail & Related papers  (2022-09-16T06:36:06Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• Simplicial Attention Networks [4.401427499962144]
  Simplicial Neural Networks (SNNs) naturally model interactions by performing message passing on simplicial complexes. We propose Simplicial Attention Networks (SAT), a new type of simplicial network that dynamically weighs the interactions between neighbouring simplicies. We demonstrate that SAT outperforms existent convolutional SNNs and GNNs in two image and trajectory classification tasks.
  arXiv  Detail & Related papers  (2022-04-20T13:41:50Z)
• Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structure [4.477401614534202]
  We transform the random graph theory into an NN model with practical meaning and based on clarifying the input-output relationship of each neuron. Under the usage of this low-operation cost approach, neurons are assigned to several groups of which connection relationships can be regarded as uniform representations of random graphs they belong to. We develop a joint classification mechanism involving information interaction between multiple RGNNs and realize significant performance improvements in supervised learning for three benchmark tasks.
  arXiv  Detail & Related papers  (2021-11-17T03:37:06Z)
• 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)
• 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)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

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.