Scholarlink

We introduce a novel technique for sampling particle physics model parameter space using Nested Sampling (NS) enhanced by multiple Machine Learning (ML) networks, including Self-Normalizing Networks (SNN) and Normalizing Flows (Real-NVP). To demonstrate its effectiveness, we apply this approach to the Type-II Seesaw model. Our Bayesian analysis explores the model parameter space while incorporating theoretical constraints and experimental data related to the 125 GeV Higgs boson, the \(\rho \) -parameter, and oblique parameters.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Boosting Beyond Standard Model Searches: ML-Enhanced Nested-Sampling for Rapid Parameter Estimation

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rajneil Baruah,
  • Subhadeep Mondal,
  • Sunando Kumar Patra,
  • Satyajit Roy

摘要

We introduce a novel technique for sampling particle physics model parameter space using Nested Sampling (NS) enhanced by multiple Machine Learning (ML) networks, including Self-Normalizing Networks (SNN) and Normalizing Flows (Real-NVP). To demonstrate its effectiveness, we apply this approach to the Type-II Seesaw model. Our Bayesian analysis explores the model parameter space while incorporating theoretical constraints and experimental data related to the 125 GeV Higgs boson, the \(\rho \) -parameter, and oblique parameters.