Neural networks in non-metric spaces

• URL: http://arxiv.org/abs/2406.09310v1
• Date: Thu, 13 Jun 2024 16:44:58 GMT
• Title: Neural networks in non-metric spaces
• Authors: Luca Galimberti,
• Abstract summary: We prove several universal approximation theorems for a vast class of input and output spaces. We show that our neural network architectures can be projected down to "finite dimensional" subspaces with any desirable accuracy. The resulting neural network architecture is therefore applicable for prediction tasks based on functional data.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Leveraging the infinite dimensional neural network architecture we proposed in arXiv:2109.13512v4 and which can process inputs from Fr\'echet spaces, and using the universal approximation property shown therein, we now largely extend the scope of this architecture by proving several universal approximation theorems for a vast class of input and output spaces. More precisely, the input space $\mathfrak X$ is allowed to be a general topological space satisfying only a mild condition ("quasi-Polish"), and the output space can be either another quasi-Polish space $\mathfrak Y$ or a topological vector space $E$. Similarly to arXiv:2109.13512v4, we show furthermore that our neural network architectures can be projected down to "finite dimensional" subspaces with any desirable accuracy, thus obtaining approximating networks that are easy to implement and allow for fast computation and fitting. The resulting neural network architecture is therefore applicable for prediction tasks based on functional data. To the best of our knowledge, this is the first result which deals with such a wide class of input/output spaces and simultaneously guarantees the numerical feasibility of the ensuing architectures. Finally, we prove an obstruction result which indicates that the category of quasi-Polish spaces is in a certain sense the correct category to work with if one aims at constructing approximating architectures on infinite-dimensional spaces $\mathfrak X$ which, at the same time, have sufficient expressive power to approximate continuous functions on $\mathfrak X$, are specified by a finite number of parameters only and are "stable" with respect to these parameters.

Related papers

• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Multi-layer random features and the approximation power of neural networks [4.178980693837599]
  We prove that a reproducing kernel Hilbert space contains only functions that can be approximated by the architecture. We show that if eigenvalues of the integral operator of the NNGP decay slower than $k-n-frac23$ where $k$ is an order of an eigenvalue, our theorem guarantees a more succinct neural network approximation than Barron's theorem.
  arXiv  Detail & Related papers  (2024-04-26T14:57:56Z)
• An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning [25.25903127886586]
  We build universal functions approximators of continuous maps between arbitrary Polish metric spaces $mathcalX$ and $mathcalY$. In particular, we show that the required number of Dirac measures is determined by the structure of $mathcalX$ and $mathcalY$.
  arXiv  Detail & Related papers  (2023-04-24T16:18:22Z)
• Exponential Separations in Symmetric Neural Networks [48.80300074254758]
  We consider symmetric Networkparencitesantoro 2017simple architecture as a natural generalization of DeepSetsparencitezaheerdeep architecture. Under the restriction to analytic activation functions, we construct a symmetric function acting on sets of dimensions $N$ in dimension with $D$.
  arXiv  Detail & Related papers  (2022-06-02T19:45:10Z)
• A singular Riemannian geometry approach to Deep Neural Networks II. Reconstruction of 1-D equivalence classes [78.120734120667]
  We build the preimage of a point in the output manifold in the input space. We focus for simplicity on the case of neural networks maps from n-dimensional real spaces to (n - 1)-dimensional real spaces.
  arXiv  Detail & Related papers  (2021-12-17T11:47:45Z)
• Sobolev-type embeddings for neural network approximation spaces [5.863264019032882]
  We consider neural network approximation spaces that classify functions according to the rate at which they can be approximated. We prove embedding theorems between these spaces for different values of $p$. We find that, analogous to the case of classical function spaces, it is possible to trade "smoothness" (i.e., approximation rate) for increased integrability.
  arXiv  Detail & Related papers  (2021-10-28T17:11:38Z)
• 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)
• Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers [50.85524803885483]
  This work proposes a formal definition of statistically meaningful (SM) approximation which requires the approximating network to exhibit good statistical learnability. We study SM approximation for two function classes: circuits and Turing machines.
  arXiv  Detail & Related papers  (2021-07-28T04:28:55Z)
• Quantitative Rates and Fundamental Obstructions to Non-Euclidean Universal Approximation with Deep Narrow Feed-Forward Networks [3.8073142980733]
  We quantify the number of narrow layers required for "deep geometric feed-forward neural networks" We find that both the global and local universal approximation guarantees can only coincide when approximating null-homotopic functions.
  arXiv  Detail & Related papers  (2021-01-13T23:29:40Z)
• Non-Euclidean Universal Approximation [4.18804572788063]
  Modifications to a neural network's input and output layers are often required to accommodate the specificities of most practical learning tasks. We present general conditions describing feature and readout maps that preserve an architecture's ability to approximate any continuous functions uniformly on compacts.
  arXiv  Detail & Related papers  (2020-06-03T15:38:57Z)
• Neural Operator: Graph Kernel Network for Partial Differential Equations [57.90284928158383]
  This work is to generalize neural networks so that they can learn mappings between infinite-dimensional spaces (operators) We formulate approximation of the infinite-dimensional mapping by composing nonlinear activation functions and a class of integral operators. Experiments confirm that the proposed graph kernel network does have the desired properties and show competitive performance compared to the state of the art solvers.
  arXiv  Detail & Related papers  (2020-03-07T01:56:20Z)

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.