Müntz-Szász Networks: Neural Architectures with Learnable Power-Law Bases

📅 2025-12-22
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Many physical models exhibit singularities—e.g., boundary layers or $|x|^alpha$-type behavior in fracture mechanics—where standard neural networks, constrained by fixed activation functions, suffer from poor approximation efficiency. To address this, we propose a learnable power-law basis network, the first architecture to explicitly embed the Müntz–Szász approximation theorem. Its activation function, $varphi(x)=sum a_k|x|^{mu_k}+sum b_koperatorname{sign}(x)|x|^{lambda_k}$, features jointly learnable exponents $mu_k,lambda_k$ and coefficients. We prove its universal approximation property and derive a squared-order error bound strictly superior to that of multilayer perceptrons (MLPs). Experiments demonstrate: (i) 5–8× lower error and 10× fewer parameters on singular regression tasks; (ii) 3–6× higher accuracy on physics-informed neural network (PINN) benchmarks; and (iii) learned exponents that quantitatively recover the true singularity structure of analytical solutions.

Technology Category

Application Category

📝 Abstract
Standard neural network architectures employ fixed activation functions (ReLU, tanh, sigmoid) that are poorly suited for approximating functions with singular or fractional power behavior, a structure that arises ubiquitously in physics, including boundary layers, fracture mechanics, and corner singularities. We introduce Müntz-Szász Networks (MSN), a novel architecture that replaces fixed smooth activations with learnable fractional power bases grounded in classical approximation theory. Each MSN edge computes $φ(x) = sum_k a_k |x|^{μ_k} + sum_k b_k mathrm{sign}(x)|x|^{λ_k}$, where the exponents ${μ_k, λ_k}$ are learned alongside the coefficients. We prove that MSN inherits universal approximation from the Müntz-Szász theorem and establish novel approximation rates: for functions of the form $|x|^α$, MSN achieves error $mathcal{O}(|μ- α|^2)$ with a single learned exponent, whereas standard MLPs require $mathcal{O}(ε^{-1/α})$ neurons for comparable accuracy. On supervised regression with singular target functions, MSN achieves 5-8x lower error than MLPs with 10x fewer parameters. Physics-informed neural networks (PINNs) represent a particularly demanding application for singular function approximation; on PINN benchmarks including a singular ODE and stiff boundary-layer problems, MSN achieves 3-6x improvement while learning interpretable exponents that match the known solution structure. Our results demonstrate that theory-guided architectural design can yield dramatic improvements for scientifically-motivated function classes.
Problem

Research questions and friction points this paper is trying to address.

Approximating singular or fractional power functions in physics
Improving accuracy with fewer parameters in neural networks
Enhancing physics-informed neural networks for singular problems
Innovation

Methods, ideas, or system contributions that make the work stand out.

Learnable fractional power bases replace fixed activations
Exponents and coefficients learned jointly for singular functions
Theory-guided architecture improves physics-informed neural networks
🔎 Similar Papers
G
Gnankan Landry Regis N'guessan
Axiom Research Group, Department of Applied Mathematics and Computational Science, The Nelson Mandela African Institution of Science and Technology (NM-AIST), Arusha, Tanzania, African Institute for Mathematical Sciences (AIMS), Research and Innovation Centre (RIC), Kigali, Rwanda