BIMSA >
BIMSA Lecture
Adjoint Path-Kernel Method for Backpropogation and Data Assimilation in Unstable Diffusions
Adjoint Path-Kernel Method for Backpropogation and Data Assimilation in Unstable Diffusions
组织者
孙泽钜
演讲者
倪昂修
时间
2025年12月20日 11:00 至 12:00
地点
Online
线上
Zoom 559 700 6085
(BIMSA)
摘要
We derive the adjoint path-kernel method for computing parameter-gradients (linear responses) of SDEs. Its cost is almost independent of the number of parameters, and it works for non-hyperbolic systems with parameter-controlled multiplicative noise. With this new formula, we extend the conventional backpropagation method to settings with gradient explosion, and demonstrate it on the 40-dimensional Lorenz 96 system.
Moreover, we consider a difficult version of the 4D-Var data assimilation problem where (1) the deterministic part of the model is chaotic, (2) the loss is a single long-time functional accounting for discrepancies in both the observations and the dynamics, (3) some parameters in the dynamics are unknown, and (4) some coordinates of the states cannot be observed, and cannot be reasonably inferred from other coordinates within a short time. We model the correction term at each time-step separately as a parameterized function of the random state. With our new tool, we can run stochastic gradient descent to find the path and parameters that best match the low-dimensional observation data. We demonstrate this on the 10D Lorenz-96 system with 8D observations.
Moreover, we consider a difficult version of the 4D-Var data assimilation problem where (1) the deterministic part of the model is chaotic, (2) the loss is a single long-time functional accounting for discrepancies in both the observations and the dynamics, (3) some parameters in the dynamics are unknown, and (4) some coordinates of the states cannot be observed, and cannot be reasonably inferred from other coordinates within a short time. We model the correction term at each time-step separately as a parameterized function of the random state. With our new tool, we can run stochastic gradient descent to find the path and parameters that best match the low-dimensional observation data. We demonstrate this on the 10D Lorenz-96 system with 8D observations.