This paper investigates the high minima of Gaussian processes, focusing on overshoots and the locations of minimizers. It demonstrates that under certain conditions, the scaled overshoot converges to an exponential random variable as the minimum value increases. The research also shows that weak subsequential limits of conditional laws for minimizers correspond to optimal covariance-energy measures, with convergence occurring if this measure is unique. These findings are illustrated using examples such as stationary Gaussian processes, fractional Brownian motion, and fractional Brownian sheets. AI
IMPACT Provides theoretical underpinnings for understanding complex data distributions in machine learning.
RANK_REASON Academic paper on a specific statistical modeling technique. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
