Linear dynamical systems, a.k.a. Kalman filtering, are a class of time-series models widely used in robotics, finance, engineering, and meteorology. In it's general form (unknown system), 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 linear dynamical systems with multi-dimensional inputs, outputs, and a latent state. This approach yields a simple & efficient algorithms for low-regret prediction (i.e. asymptotically vanishing MSE) as well as finite-time control. The talk will cover several results, which are joint work with Karan Singh, Cyril Zhang, Sanjeev Arora, Holden Lee, and Yi Zhang.
You are here
Elad Hazan, Princeton UniversityTitle: Taking Control by Convex OptimizationAbstract:Bio: Elad Hazan is a professor of computer science at Princeton university. His research focuses on the design and analysis of algorithms for basic problems in machine learning and optimization. Amongst his contributions are the co-development of the AdaGrad algorithm for training learning machines, and the first sublinear-time algorithms for convex optimization. He is the recipient of the IBM Goldberg best paper award in 2012 for contributions to sublinear time algorithms for machine learning, and in 2008 for decision making under uncertainty, a European Research Council grant , a Marie Curie fellowship, Google Research Awards and the Bell Labs prize.