Researchers have developed a novel method for inferring parameters of stochastic differential equations (SDEs) driven by a specific type of Gaussian process. This approach utilizes neural networks and an Euler approximation to estimate drift, diffusion, and noise covariance from discrete observations. The method models the drift and diffusion coefficients using neural and radial-basis representations, and then estimates the covariance exponent and diffusion scale through a likelihood profile, showing promising results compared to alternative neural methods. AI
IMPACT This research advances methods for parameter inference in complex stochastic systems, potentially improving the modeling and simulation capabilities of AI systems that rely on such mathematical frameworks.
RANK_REASON The item is an academic paper submitted to arXiv in the stat.ML category, detailing a new inference method for stochastic differential equations. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- Gaussian Processes
- Jose Hermenegildo Ramirez Gonzalez
- Neural Networks
- radial basis function network
- stat.ML
- stochastic differential equations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
