neural sdes

**Neural SDEs** are a **class of generative and discriminative models that parameterize both the drift and diffusion of a stochastic differential equation with neural networks** — enabling continuous-time latent variable models, continuous normalizing flows with noise, and uncertainty-aware predictions. **Training Neural SDEs** - **Variational**: Use variational inference with a posterior SDE and prior SDE. - **Score Matching**: Train the score function $ abla log p_t(z)$ for generative modeling. - **Adjoint Method**: Backpropagate through the SDE solver using the stochastic adjoint method. - **KL Divergence**: The KL between path measures of two SDEs has a tractable form (Girsanov theorem). **Why It Matters** - **Diffusion Models**: Score-based generative models (DDPM, score matching) can be viewed through the Neural SDE lens. - **Continuous Latent Dynamics**: Model continuous-time stochastic processes in latent space (finance, physics). - **Theory + Practice**: Neural SDEs connect deep learning to the rich mathematical theory of stochastic processes. **Neural SDEs** are **deep learning meets stochastic calculus** — combining neural network expressiveness with the mathematical framework of stochastic processes.