English
Related papers

Related papers: Generative Neural Operators of Log-Complexity Can …

200 papers

Although optimization is the longstanding algorithmic backbone of machine learning, new models still require the time-consuming implementation of new solvers. As a result, there are thousands of implementations of optimization algorithms…

Machine Learning · Computer Science 2019-06-03 Sören Laue , Matthias Mitterreiter , Joachim Giesen

Neural operator (NO) architectures learn nonlinear maps between infinite-dimensional function spaces and are widely used to accelerate simulation and enable data-driven model discovery. While universality results ensure expressivity, they…

Optimization and Control · Mathematics 2026-03-02 Takashi Furuya , Anastasis Kratsios

We present statistical convergence results for the learning of (possibly) non-linear mappings in infinite-dimensional spaces. Specifically, given a map $G_0:\mathcal X\to\mathcal Y$ between two separable Hilbert spaces, we analyze the…

Statistics Theory · Mathematics 2024-12-24 Niklas Reinhardt , Sven Wang , Jakob Zech

We introduce Geometric Neural Operators (GNPs) for accounting for geometric contributions in data-driven deep learning of operators. We show how GNPs can be used (i) to estimate geometric properties, such as the metric and curvatures, (ii)…

Machine Learning · Computer Science 2024-04-18 Blaine Quackenbush , Paul J. Atzberger

Neural operators have emerged as transformative tools for learning mappings between infinite-dimensional function spaces, offering useful applications in solving complex partial differential equations (PDEs). This paper presents a rigorous…

Numerical Analysis · Mathematics 2026-01-23 Vu-Anh Le , Mehmet Dik

Generative models in function spaces, situated at the intersection of generative modeling and operator learning, are attracting increasing attention due to their immense potential in diverse scientific and engineering applications. While…

Machine Learning · Computer Science 2025-10-30 Yaozhong Shi , Zachary E. Ross , Domniki Asimaki , Kamyar Azizzadenesheli

Neural operators effectively solve PDE problems from data without knowing the explicit equations, which learn the map from the input sequences of observed samples to the predicted values. Most existing works build the model in the original…

Machine Learning · Computer Science 2024-12-23 Tian Wang , Chuang Wang

Neural operators are capable of capturing nonlinear mappings between infinite-dimensional functional spaces, offering a data-driven approach to modeling complex functional relationships in classical density functional theory (cDFT). In this…

Solving parametric partial differential equations (PDEs) and associated PDE-based, inverse problems is a central task in engineering and physics, yet existing neural operator methods struggle with high-dimensional, discontinuous inputs and…

Machine Learning · Computer Science 2025-07-03 Yaohua Zang , Phaedon-Stelios Koutsourelakis

As an alternative to classical numerical solvers for partial differential equations (PDEs) subject to boundary value constraints, there has been a surge of interest in investigating neural networks that can solve such problems efficiently.…

Machine Learning · Computer Science 2023-08-21 Winfried Lötzsch , Simon Ohler , Johannes S. Otterbach

Combinatorial optimization problems (COPs) are an important research topic in various fields. In recent times, there have been many attempts to solve COPs using deep learning-based approaches. We propose a novel neural network model that…

Computational Geometry · Computer Science 2023-04-17 Jaeseung Lee , Woojin Choi , Jibum Kim

Neural Operators (NOs) are a leading method for surrogate modeling of partial differential equations. Unlike traditional neural networks, which approximate individual functions, NOs learn the mappings between function spaces. While NOs have…

Astrophysics of Galaxies · Physics 2025-08-01 Keith Poletti , Stella S. R. Offner , Rachel A. Ward

Learning maps between function spaces with a strong inductive bias is a central challenge in soft computing, especially when training data are scarce and standard deep architectures overfit. We introduce a \emph{neural integral operator}…

Machine Learning · Computer Science 2026-05-26 Emanuele Zappala , Alice Giola , Andreas Kramer , Saugat Acharya , Enrico Greco

Fourier Neural Operators (FNOs) have emerged as leading surrogates for solver operators for various functional problems, yet their stability, generalization and frequency behavior lack a principled explanation. We present a systematic…

Machine Learning · Computer Science 2026-02-05 Taeyoung Kim

Neural operators perform well on structured domains, yet their behaviour on irregular geometries remains poorly understood. We show that this limitation is not merely an encoding issue, but a depth-wise failure mode inherent to deep…

Machine Learning · Computer Science 2026-05-08 Yanming Xia , Angelica I. Aviles-Rivero

In this work, we introduce a planning neural operator (PNO) for predicting the value function of a motion planning problem. We recast value function approximation as learning a single operator from the cost function space to the value…

Robotics · Computer Science 2025-05-28 Sharath Matada , Luke Bhan , Yuanyuan Shi , Nikolay Atanasov

Neural operators are neural network-based surrogate models for approximating solution operators of parametric partial differential equations, enabling efficient many-query computations in science and engineering. Many applications,…

Numerical Analysis · Mathematics 2026-02-03 Mingyu Han , Daniel Zhengyu Huang , Yuhan Wang , Yanshu Zhang , Jiayi Zhou

While many problems in machine learning focus on learning mappings between finite-dimensional spaces, scientific applications require approximating mappings between function spaces, i.e., operators. We study the problem of learning…

Machine Learning · Computer Science 2025-10-30 Adrien Weihs , Jingmin Sun , Zecheng Zhang , Hayden Schaeffer

Recently, operator learning, or learning mappings between infinite-dimensional function spaces, has garnered significant attention, notably in relation to learning partial differential equations from data. Conceptually clear when outlined…

Elliptic partial differential equations (PDEs) are a major class of time-independent PDEs that play a key role in many scientific and engineering domains such as fluid dynamics, plasma physics, and solid mechanics. Recently, neural…

Machine Learning · Computer Science 2024-01-18 Haixin Wang , Jiaxin Li , Anubhav Dwivedi , Kentaro Hara , Tailin Wu