Simulation-Free Schrödinger Bridges via Score and Flow Matching: A Detailed Analysis
The authors introduce [SF]2M, a simulation-free objective for inferring stochastic dynamics efficiently. By leveraging entropic optimal transport and neural networks, [SF]2M outperforms existing methods in modeling Schrödinger bridges accurately.
Inferring Stochastic Dynamics with Lévy Noise Using Weak Collocation Regression
The author proposes a Weak Collocation Regression method to reveal unknown stochastic dynamical systems with both α-stable Lévy noise and Gaussian noise, demonstrating accuracy and computational efficiency.
Inferring Force Fields from Cross-Sectional Biological Data Using Probability Flow Inference (PFI) with a Focus on Molecular Noise
Accurately inferring the dynamics of biological processes from cross-sectional data requires accounting for intrinsic noise, especially molecular noise, and the Probability Flow Inference (PFI) method offers a computationally efficient way to achieve this by leveraging score-based generative models and incorporating realistic noise priors.
