Archives AI News

FEDONet : Fourier-Embedded DeepONet for Spectrally Accurate Operator Learning

arXiv:2509.12344v1 Announce Type: new Abstract: Deep Operator Networks (DeepONets) have recently emerged as powerful data-driven frameworks for learning nonlinear operators, particularly suited for approximating solutions to partial differential equations (PDEs). Despite their promising capabilities, the standard implementation of DeepONets, which…

Safe Learning Under Irreversible Dynamics via Asking for Help

arXiv:2502.14043v2 Announce Type: replace Abstract: Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from…

Spontaneous Kolmogorov-Arnold Geometry in Shallow MLPs

arXiv:2509.12326v1 Announce Type: new Abstract: The Kolmogorov-Arnold (KA) representation theorem constructs universal, but highly non-smooth inner functions (the first layer map) in a single (non-linear) hidden layer neural network. Such universal functions have a distinctive local geometry, a “texture,” which…

QDFlow: A Python package for physics simulations of quantum dot devices

arXiv:2509.13298v1 Announce Type: cross Abstract: Recent advances in machine learning (ML) have accelerated progress in calibrating and operating quantum dot (QD) devices. However, most ML approaches rely on access to large, high-quality labeled datasets for training, benchmarking, and validation, with…

Concentration inequalities for semidefinite least squares based on data

arXiv:2509.13166v1 Announce Type: cross Abstract: We study data-driven least squares (LS) problems with semidefinite (SD) constraints and derive finite-sample guarantees on the spectrum of their optimal solutions when these constraints are relaxed. In particular, we provide a high confidence bound…

Prediction of Stocks Index Price using Quantum GANs

arXiv:2509.12286v1 Announce Type: new Abstract: This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) for stock price prediction. Financial markets are inherently complex, marked by high volatility and intricate patterns that traditional models often fail to capture. QGANs,…