{"ID":2871364,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.11284","arxiv_id":"2509.11284","title":"PINGS: Physics-Informed Neural Network for Fast Generative Sampling","abstract":"We introduce PINGS (Physics-Informed Neural Network for Fast Generative Sampling), a framework that amortizes diffusion sampling by training a physics-informed network to approximate reverse-time probability-flow dynamics, reducing sampling to a single forward pass (NFE = 1). As a proof of concept, we learn a direct map from a 3D standard normal to a non-Gaussian Gaussian Mixture Model (GMM). PINGS preserves the target's distributional structure (multi-bandwidth kernel $MMD^2 = 1.88 \\times 10^{-2}$ with small errors in mean, covariance, skewness, and excess kurtosis) and achieves constant-time generation: $10^4$ samples in $16.54 \\pm 0.56$ millisecond on an RTX 3090, versus 468-843 millisecond for DPM-Solver (10/20) and 960 millisecond for DDIM (50) under matched conditions. We also sanity-check the PINN/automatic-differentiation pipeline on a damped harmonic oscillator, obtaining MSEs down to $\\mathcal{O}(10^{-5})$. Compared to fast but iterative ODE solvers and direct-map families (Flow, Rectified-Flow, Consistency), PINGS frames generative sampling as a PINN-style residual problem with endpoint anchoring, yielding a white-box, differentiable map with NFE = 1. These proof-of-concept results position PINGS as a promising route to fast, function-based generative sampling with potential extensions to scientific simulation (e.g., fast calorimetry).","short_abstract":"We introduce PINGS (Physics-Informed Neural Network for Fast Generative Sampling), a framework that amortizes diffusion sampling by training a physics-informed network to approximate reverse-time probability-flow dynamics, reducing sampling to a single forward pass (NFE = 1). As a proof of concept, we learn a direct ma...","url_abs":"https://arxiv.org/abs/2509.11284","url_pdf":"https://arxiv.org/pdf/2509.11284v1","authors":"[\"Achmad Ardani Prasha\",\"Clavino Ourizqi Rachmadi\",\"Muhamad Fauzan Ibnu Syahlan\",\"Naufal Rahfi Anugerah\",\"Nanda Garin Raditya\",\"Putri Amelia\",\"Sabrina Laila Mutiara\",\"Hilman Syachr Ramadhan\"]","published":"2025-09-14T14:22:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"physics.comp-ph\"]","methods":"[\"Diffusion Model\"]","has_code":false}