Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities

• URL: http://arxiv.org/abs/2602.08419v1
• Date: Mon, 09 Feb 2026 09:25:37 GMT
• Title: Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities
• Abstract summary: Radial Mntz-Szsz Networks (RMN) represent fields as linear combinations of learnable radial powers $r$, including negative exponents.<n>RMN achieves 1.5$times$-51$times$ lower RMSE than coordinates and 10$times$--100$times$ lower RMSE than SIREN.
• Score: 3.1861308132183375
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radial singular fields, such as $1/r$, $\log r$, and crack-tip profiles, are difficult to model for coordinate-separable neural architectures. We show that any $C^2$ function that is both radial and additively separable must be quadratic, establishing a fundamental obstruction for coordinate-wise power-law models. Motivated by this result, we introduce Radial Müntz-Szász Networks (RMN), which represent fields as linear combinations of learnable radial powers $r^μ$, including negative exponents, together with a limit-stable log-primitive for exact $\log r$ behavior. RMN admits closed-form spatial gradients and Laplacians, enabling physics-informed learning on punctured domains. Across ten 2D and 3D benchmarks, RMN achieves 1.5$\times$--51$\times$ lower RMSE than MLPs and 10$\times$--100$\times$ lower RMSE than SIREN while using 27 parameters, compared with 33,537 for MLPs and 8,577 for SIREN. We extend RMN to angular dependence (RMN-Angular) and to multiple sources with learnable centers (RMN-MC); when optimization converges, source-center recovery errors fall below $10^{-4}$. We also report controlled failures on smooth, strongly non-radial targets to delineate RMN's operating regime.

Related papers

• Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks [38.61040361525374]
  An input may activate few hidden units even when different inputs collectively use an entire network.<n>We study the statistical complexity of this input-dependent sparsity in the one-hidden-layer ReLU model.
  arXiv  Detail & Related papers  (2026-09-08T17:53:03Z)
• DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion [1.2031796234206138]
  DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data.<n>The framework regresses four earth-model parameters and reconstructs profiles using a differentiable soft-step decoder.<n>The framework demonstrates high robustness to noise through curriculum-based amplitude augmentation, maintaining a mean $barR2$ of 0.858 at $pm2%$ random amplitude error.
  arXiv  Detail & Related papers  (2026-05-06T14:58:17Z)
• Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain [0.0]
  Byzantine clients poison gradients under heterogeneous (Non-IID) data.<n>We propose Spectral Sentinel, a Byzantine detection and aggregation framework.<n>We implement the full system with blockchain integration on Polygon networks.
  arXiv  Detail & Related papers  (2025-12-14T09:43:03Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• Machine-Learning Accelerated Calculations of Reduced Density Matrices [0.3823356975862005]
  We propose to use neural network (NN) architectures to accelerate the calculation of, and even predict, the $n$-RDMs for large-size systems.<n>The underlying intuition is that $n$-RDMs are often smooth functions over the Brillouin zone (BZ) and are thus interpolable, allowing NNs trained on small-size $n$-RDMs to predict large-size ones.
  arXiv  Detail & Related papers  (2025-11-10T18:23:34Z)
• Trace Regularity PINNs: Enforcing $\mathrm{H}^{\frac{1}{2}}(\partial Ω)$ for Boundary Data [0.48342038441006796]
  We propose an enhanced physics-informed neural network (PINN)<n>The Trace Regularity Physics-Informed Neural Network (TRPINN) enforces the boundary loss in the Sobolev-Slobodeckij norm $H1/2(partial Omega)$.<n>By incorporating the exact $H1/2(partial Omega)$ norm, we show that the approximation converges to the true solution in the $H1(Omega)$ sense.
  arXiv  Detail & Related papers  (2025-10-19T13:08:16Z)
• Neural PDE Solvers with Physics Constraints: A Comparative Study of PINNs, DRM, and WANs [1.131316248570352]
  Partial equations (PDEs) underpin models across science and engineering, yet analytical solutions are atypical and classical mesh-based solvers can be costly in high dimensions.<n>This dissertation presents a unified comparison of three mesh-free neural PDE solvers, physics-informed neural networks (PINNs), the deep Ritz method (DRM), and weak adversarial networks (WANs), on Poisson problems (up to 5D) and the time-independent Schr"odinger equation in 1D/2D.
  arXiv  Detail & Related papers  (2025-10-09T13:41:51Z)
• VAE-DNN: Energy-Efficient Trainable-by-Parts Surrogate Model For Parametric Partial Differential Equations [49.1574468325115]
  We propose a trainable-by-parts surrogate model for solving forward and inverse parameterized nonlinear partial differential equations.<n>The proposed approach employs an encoder to reduce the high-dimensional input $y(bmx)$ to a lower-dimensional latent space, $bmmu_bmphi_y$.<n>A fully connected neural network is used to map $bmmu_bmphi_y$ to the latent space, $bmmu_bmphi_h$, of the P
  arXiv  Detail & Related papers  (2025-08-05T18:37:32Z)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit [75.4661041626338]
  We study the problem of gradient descent learning of a single-index target function $f_*(boldsymbolx) = textstylesigma_*left(langleboldsymbolx,boldsymbolthetarangleright)$<n>We prove that a two-layer neural network optimized by an SGD-based algorithm learns $f_*$ with a complexity that is not governed by information exponents.
  arXiv  Detail & Related papers  (2024-06-03T17:56:58Z)
• On the Magnetization of the $120^\circ$ order of the Spin-1/2 Triangular Lattice Heisenberg Model: a DMRG revisit [0.552480439325792]
  We revisit the issue about the magnetization of the $120circ$ order in the spin-1/2 triangular lattice Heisenberg model (TLHM) with Density Matrix Renormalization Group (DMRG) The accurate determination of the magnetization of this model is challenging for numerical methods and its value exhibits substantial disparities across various methods.
  arXiv  Detail & Related papers  (2023-10-18T08:08:06Z)
• Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds [75.51968172401394]
  We study the sample complexity of the neural policy mirror descent (NPMD) algorithm with deep convolutional neural networks (CNN) In each iteration of NPMD, both the value function and the policy can be well approximated by CNNs. We show that NPMD can leverage the low-dimensional structure of state space to escape from the curse of dimensionality.
  arXiv  Detail & Related papers  (2023-09-25T07:31:22Z)
• Neural Inference of Gaussian Processes for Time Series Data of Quasars [72.79083473275742]
  We introduce a new model that enables it to describe quasar spectra completely. We also introduce a new method of inference of Gaussian process parameters, which we call $textitNeural Inference$. The combination of both the CDRW model and Neural Inference significantly outperforms the baseline DRW and MLE.
  arXiv  Detail & Related papers  (2022-11-17T13:01:26Z)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes [15.76663241036412]
  We prove for a large class of activation functions that, if the model memorizes even a fraction of the training, then its Sobolev-seminorm is lower-bounded. Experiments reveal for the first time, (iv) a multiple-descent phenomenon in the robustness of the min-norm interpolator.
  arXiv  Detail & Related papers  (2021-06-04T17:52:50Z)

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.