A new arXiv paper introduces a method for achieving global universality in non-anticipative and path-dependent functionals using discrete-time signatures. The research establishes that linear functionals of these signatures can approximate various Gaussian processes, including Brownian motion and fractional Brownian motion with a Hurst parameter greater than 1/4. The findings also yield approximation results for random and stochastic differential equations driven by Brownian motion. AI
IMPACT This research could lead to more robust and universal approximation capabilities for complex time-series data and stochastic systems.
RANK_REASON The cluster contains a single academic paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- Brownian motion
- Fractional Brownian motion
- Gaussian Processes
- Mihriban Ceylan
- Stochastic Differential Equations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →