Victor Geadah

@vgeadah.bsky.social

PhD student in statistical neuroscience at Princeton. https://victorgeadah.github.io

In a system subject to unobserved control, can you infer both the underlying dynamics and the control objective? 🤔 A year ago, I was presenting our work at IEEE CDC on solving this problem for stochastic LQR. arxiv.org/abs/2502.15014 Short 🧵 on the results, and how I think about them a year later.

A neural population of dynamics x_t, the "system", is subject to control via inputs u_t. These inputs may come from the population itself or some other unobserved system. We only get partial observations y_t of the system in x_t, in the form of neural recordings.

At #NeurIPS2025! 🎉 Excited to present Conditionally Linear Dynamical Systems (CLDS). We leverage the dependence of neural dynamics on task covariates to yield an interpretable, flexible model of dynamics. Come meet and check it out! 📍: Poster #2209, Hall C,D,E on Thu Dec 4, 11 am–2 pm, PST. 🧵/6