paper-with-me

홈 › Papers

Generative Models and Statistical Validation

2026-05-28 · Sascha Diefenbacher, Sofia Palacios Schweitzer, Gregor Kasieczka arxiv

Generative machine learning has become an essential tool in theoretical and experimental physics, especially in the context of fast surrogates and density estimators. In this work, we first introduce the underlying framework of modern generative networks and then discuss challenges in quantifying their accuracy, precision, and statistical power.

📄 PDF Abstract BibTeX arXiv:2605.30453

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning to Validate Generative Models: a Goodness-of-Fit Approach

2025-11-12 · Pietro Cappelli, Gaia Grosso, Marco Letizia, Humberto Reyes-González 외 arxiv

Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous validation. Classic approaches struggle…

Generative Adversarial Networks to infer velocity components in rotating turbulent flows

2023-01-18 · Tianyi Li, Michele Buzzicotti, Luca Biferale, Fabio Bonaccorso

Inference problems for two-dimensional snapshots of rotating turbulent flows are studied. We perform a systematic quantitative benchmark of point-wise and statistical reconstruction capabilities of the linear Extended Pr…

Generative Adversarial Network

Physics-informed simulation framework for realistic sonar image generation and statistical validation

2026-05-19 · Kamal Basha S, Athira Nambiar arxiv

Synthetic sonar datasets offer a scalable alternative to costly real-world acquisition, yet their utility remains limited by the absence of rigorous quantitative validation. We present ACOUSIM (ACOustic SIMulation and Va…

Image Generation

A Digital Engineering Approach to Testing Modern AI and Complex Systems

2024-11-26 · Joseph R. Guerci, Sandeep Gogineni, Robert W. Schutz, Gavin I. McGee 외

Modern AI (i.e., Deep Learning and its variants) is here to stay. However, its enigmatic black box nature presents a fundamental challenge to the traditional methods of test and validation (T&E). Or does it? In this pape…

Deep Learning

Watermarking Generative Categorical Data

2024-11-16 · Bochao Gu, Hengzhi He, Guang Cheng

In this paper, we propose a novel statistical framework for watermarking generative categorical data. Our method systematically embeds pre-agreed secret signals by splitting the data distribution into two components and …

Synthetic Data Generation