IC Colloquium: The Non-Stochastic Control Problem
Event details
| Date | 22.11.2019 |
| Hour | 16:15 › 17:15 |
| Location | |
| Category | Conferences - Seminars |
By: Elad Hazan - Princeton University
Video of his talk
Abstract:
Linear dynamical systems are a continuous subclass of reinforcement learning models that are widely used in robotics, finance, engineering, and meteorology.
Classical control, since the work of Kalman, has focused on dynamics with Gaussian i.i.d. noise, quadratic loss functions and, in terms of provably efficient algorithms, known systems and observed state.
We'll discuss how to apply new machine learning methods to control which relax all of the above: efficient control with adversarial noise, general loss functions, unknown systems, and partial observation.
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 optimization algorithm, and the first sublinear-time algorithms for convex optimization. He is the recipient of the Bell Labs prize, (twice) the IBM Goldberg best paper award in 2012 and 2008, a European Research Council grant, a Marie Curie fellowship and Google Research Award (twice). He served on the steering committee of the Association for Computational Learning and has been program chair for COLT 2015. In 2017 he co-founded In8 inc. focusing on efficient optimization and control, acquired by Google in 2018. He is the co-founder and director of Google AI Princeton.
Research interests: Control and Reinforcement Learning, Optimization for Machine Learning, Online Convex Optimization. More details and links to the relevant papers are in this page.
Link to full CV
More information
Video of his talk
Abstract:
Linear dynamical systems are a continuous subclass of reinforcement learning models that are widely used in robotics, finance, engineering, and meteorology.
Classical control, since the work of Kalman, has focused on dynamics with Gaussian i.i.d. noise, quadratic loss functions and, in terms of provably efficient algorithms, known systems and observed state.
We'll discuss how to apply new machine learning methods to control which relax all of the above: efficient control with adversarial noise, general loss functions, unknown systems, and partial observation.
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 optimization algorithm, and the first sublinear-time algorithms for convex optimization. He is the recipient of the Bell Labs prize, (twice) the IBM Goldberg best paper award in 2012 and 2008, a European Research Council grant, a Marie Curie fellowship and Google Research Award (twice). He served on the steering committee of the Association for Computational Learning and has been program chair for COLT 2015. In 2017 he co-founded In8 inc. focusing on efficient optimization and control, acquired by Google in 2018. He is the co-founder and director of Google AI Princeton.
Research interests: Control and Reinforcement Learning, Optimization for Machine Learning, Online Convex Optimization. More details and links to the relevant papers are in this page.
Link to full CV
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Hosts: Martin Jaggi and Emmanuel Abbé