Linear dynamical systems (LDSs) are a class of time-series models widely used in robotics, finance, engineering, and meteorology. In it's general form (when state transition dynamics are unknown), learning LDS is a classic non-convex problem, typically tackled with heuristics like gradient descent ("backpropagation through time") or the EM algorithm. I will present our new "spectral filtering" approach to the identification and control of discrete-time general LDSs with multi-dimensional inputs, outputs, and a latent state. This approach yields a simple, efficient, and practical algorithm for low-regret prediction (i.e. asymptotically vanishing MSE).
The talk will cover a series of results, which are joint work with Elad Hazan, Cyril Zhang, Sanjeev Arora, Holden Lee, and Yi Zhang.
I'm a PhD candidate in Computer Science at Princeton University, advised by Elad Hazan. My research is focused on reinforcement learning, and seeks to address the challenges that accompany partially observable and large (or continuous) state spaces. I'm also invested in issues concerning privacy and fairness in machine learning. I did my bachelors at IIT Kanpur, where I worked on sketch-based algorithms for machine learning, and space lower bounds in the streaming model. I've also spent time at Microsoft Research in Redmond working on program synthesis.