paper-with-me

Papers

Physics-Informed Inference Time Scaling via Simulation-Calibrated Scientific Machine Learning

2025-04-22 · Zexi Fan, Yan Sun, Shihao Yang, Yiping Lu

High-dimensional partial differential equations (PDEs) pose significant computational challenges across fields ranging from quantum chemistry to economics and finance. Although scientific machine learning (SciML) techniques offer approximate solutions, they often suffer from bias and neglect crucial physical insights. Inspired by inference-time scaling strategies in language models, we propose Simulation-Calibrated Scientific Machine Learning (SCaSML), a physics-informed framework that dynamically refines and debiases the SCiML predictions during inference by enforcing the physical laws. SCaSML leverages derived new physical laws that quantifies systematic errors and employs Monte Carlo solvers based on the Feynman-Kac and Elworthy-Bismut-Li formulas to dynamically correct the prediction. Both numerical and theoretical analysis confirms enhanced convergence rates via compute-optimal inference methods. Our numerical experiments demonstrate that SCaSML reduces errors by 20-50% compared to the base surrogate model, establishing it as the first algorithm to refine approximated solutions to high-dimensional PDE during inference. Code of SCaSML is available at https://github.com/Francis-Fan-create/SCaSML.

📄 PDF Abstract BibTeX arXiv:2504.16172

Code (1)

francis-fan-create/scasml 공식 구현 jax

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Flow Matching for Geometric Trajectory Simulation

2025-05-24 · Kiet Bennema ten Brinke, Koen Minartz, Vlado Menkovski

The simulation of N-body systems is a fundamental problem with applications in a wide range of fields, such as molecular dynamics, biochemistry, and pedestrian dynamics. Machine learning has become an invaluable tool for…

Trajectory Modeling

Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting

2025-09-16 · Hung Le, Sherif Abbas, Minh Hoang Nguyen, Van Dai Do 외 arxiv

Efficient molecular dynamics (MD) simulation is vital for understanding atomic-scale processes in materials science and biophysics. Traditional density functional theory (DFT) methods are computationally expensive, which…

Trajectory Forecasting

A 3D super-resolution of wind fields via physics-informed pixel-wise self-attention generative adversarial network

2023-12-20 · Takuya Kurihana, Kyongmin Yeo, Daniela Szwarcman, Bruce Elmegreen 외

To mitigate global warming, greenhouse gas sources need to be resolved at a high spatial resolution and monitored in time to ensure the reduction and ultimately elimination of the pollution source. However, the complexit…

Generative Adversarial NetworkSuper-Resolution

Learning Biomolecular Motion: The Physics-Informed Machine Learning Paradigm

2025-11-10 · Aaryesh Deshpande arxiv

The convergence of statistical learning and molecular physics is transforming our approach to modeling biomolecular systems. Physics-informed machine learning (PIML) offers a systematic framework that integrates data-dri…

Physics-informed Gaussian Process for Online Optimization of Particle Accelerators

2020-09-08 · Adi Hanuka, X. Huang, J. Shtalenkova, D. Kennedy 외

High-dimensional optimization is a critical challenge for operating large-scale scientific facilities. We apply a physics-informed Gaussian process (GP) optimizer to tune a complex system by conducting efficient global s…