Floating-Point Neural Networks Are Provably Robust Universal Approximators

• URL: http://arxiv.org/abs/2506.16065v2
• Date: Wed, 30 Jul 2025 01:31:24 GMT
• Title: Floating-Point Neural Networks Are Provably Robust Universal Approximators
• Authors: Geonho Hwang, Wonyeol Lee, Yeachan Park, Sejun Park, Feras Saad,
• Abstract summary: neural networks enjoy a more general interval universal approximation (IUA) theorem.<n>An open question is whether the IUA theorem still holds in the floating-point setting.<n>Our IUA theorem in the floating-point setting exhibits material differences from the real-valued setting.
• Score: 11.144011131237935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The classical universal approximation (UA) theorem for neural networks establishes mild conditions under which a feedforward neural network can approximate a continuous function $f$ with arbitrary accuracy. A recent result shows that neural networks also enjoy a more general interval universal approximation (IUA) theorem, in the sense that the abstract interpretation semantics of the network using the interval domain can approximate the direct image map of $f$ (i.e., the result of applying $f$ to a set of inputs) with arbitrary accuracy. These theorems, however, rest on the unrealistic assumption that the neural network computes over infinitely precise real numbers, whereas their software implementations in practice compute over finite-precision floating-point numbers. An open question is whether the IUA theorem still holds in the floating-point setting. This paper introduces the first IUA theorem for floating-point neural networks that proves their remarkable ability to perfectly capture the direct image map of any rounded target function $f$, showing no limits exist on their expressiveness. Our IUA theorem in the floating-point setting exhibits material differences from the real-valued setting, which reflects the fundamental distinctions between these two computational models. This theorem also implies surprising corollaries, which include (i) the existence of provably robust floating-point neural networks; and (ii) the computational completeness of the class of straight-line programs that use only floating-point additions and multiplications for the class of all floating-point programs that halt.

Related papers

• Expressive Power of ReLU and Step Networks under Floating-Point Operations [11.29958155597398]
  We show that neural networks using a binary threshold unit or ReLU can memorize any finite input/output pairs. We also show similar results on memorization and universal approximation when floating-point operations use finite bits for both significand and exponent.
  arXiv  Detail & Related papers  (2024-01-26T05:59:40Z)
• Predictions Based on Pixel Data: Insights from PDEs and Finite Differences [0.0]
  This paper deals with approximation of time sequences where each observation is a matrix. We show that with relatively small networks, we can represent exactly a class of numerical discretizations of PDEs based on the method of lines. Our network architecture is inspired by those typically adopted in the approximation of time sequences.
  arXiv  Detail & Related papers  (2023-05-01T08:54:45Z)
• Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach [64.23331120621118]
  This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks. We introduce a related embedded network and show that the embedded network can be used to provide an $ell_infty$-norm box over-approximation of the reachable sets of the original network. We apply our algorithms to train implicit neural networks on the MNIST dataset and compare the robustness of our models with the models trained via existing approaches in the literature.
  arXiv  Detail & Related papers  (2022-08-08T03:13:24Z)
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks [91.3755431537592]
  We study how random pruning of the weights affects a neural network's neural kernel (NTK) In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
  arXiv  Detail & Related papers  (2022-03-27T15:22:19Z)
• Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks [79.74580058178594]
  We analyze the performance of training a pruned neural network by analyzing the geometric structure of the objective function. We show that the convex region near a desirable model with guaranteed generalization enlarges as the neural network model is pruned.
  arXiv  Detail & Related papers  (2021-10-12T01:11:07Z)
• Deep neural network approximation of analytic functions [91.3755431537592]
  entropy bound for the spaces of neural networks with piecewise linear activation functions. We derive an oracle inequality for the expected error of the considered penalized deep neural network estimators.
  arXiv  Detail & Related papers  (2021-04-05T18:02:04Z)
• The Connection Between Approximation, Depth Separation and Learnability in Neural Networks [70.55686685872008]
  We study the connection between learnability and approximation capacity. We show that learnability with deep networks of a target function depends on the ability of simpler classes to approximate the target.
  arXiv  Detail & Related papers  (2021-01-31T11:32:30Z)
• Universal Approximation in Dropout Neural Networks [0.0]
  We prove two universal approximation theorems for a range of dropout neural networks. In the first each edge output is multiplied by its random filter, resulting in a random output. In the second each edge output is multiplied by the expectation of its filter, leading to a deterministic output.
  arXiv  Detail & Related papers  (2020-12-18T16:53:15Z)
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries [62.28265459308354]
  Network learns end-to-end mapping between spatial positions and CFD quantities. Incompress laminar steady flow past a cylinder with various shapes for its cross section is considered. Network predicts the flow fields hundreds of times faster than our conventional CFD.
  arXiv  Detail & Related papers  (2020-10-15T12:15:02Z)
• Random Vector Functional Link Networks for Function Approximation on Manifolds [8.535815777849786]
  We show that single layer neural-networks with random input-to-hidden layer weights and biases have seen success in practice. We further adapt this randomized neural network architecture to approximate functions on smooth, compact submanifolds of Euclidean space.
  arXiv  Detail & Related papers  (2020-07-30T23:50:44Z)
• Interval Universal Approximation for Neural Networks [47.767793120249095]
  We introduce the interval universal approximation (IUA) theorem. IUA shows that neural networks can approximate any continuous function $f$ as we have known for decades. We study the computational complexity of constructing neural networks that are amenable to precise interval analysis.
  arXiv  Detail & Related papers  (2020-07-12T20:43:56Z)

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.