Poster
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
Vincent Roulet · Dmitriy Drusvyatskiy · Siddhartha Srinivasa · Zaid Harchaoui
We examine popular gradient-based algorithms for nonlinear control in the light of the modern complexity analysis of first-order optimization algorithms. The examination reveals that the complexity bounds can be clearly stated in terms of calls to a computational oracle related to dynamic programming and implementable by gradient back-propagation using machine learning software libraries such as PyTorch or TensorFlow. Finally, we propose a regularized Gauss-Newton algorithm enjoying worst-case complexity bounds and improved convergence behavior in practice. The software library based on PyTorch is publicly available.
Author Information
Vincent Roulet (University of Washington)
Dima Drusvyatskiy (University of Washington)
Siddhartha Srinivasa (University of Washington)
Zaid Harchaoui (University of Washington)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: Iterative Linearized Control: Stable Algorithms and Complexity Guarantees »
Thu Jun 13th 10:10 -- 10:15 AM Room Hall B
More from the Same Authors
-
2019 Poster: A Statistical Investigation of Long Memory in Language and Music »
Alexander Greaves-Tunnell · Zaid Harchaoui -
2019 Oral: A Statistical Investigation of Long Memory in Language and Music »
Alexander Greaves-Tunnell · Zaid Harchaoui -
2018 Poster: Efficient First-Order Algorithms for Adaptive Signal Denoising »
Dmitrii Ostrovskii · Zaid Harchaoui -
2018 Oral: Efficient First-Order Algorithms for Adaptive Signal Denoising »
Dmitrii Ostrovskii · Zaid Harchaoui -
2018 Poster: Recurrent Predictive State Policy Networks »
Ahmed Hefny · Zita Marinho · Wen Sun · Siddhartha Srinivasa · Geoff Gordon -
2018 Oral: Recurrent Predictive State Policy Networks »
Ahmed Hefny · Zita Marinho · Wen Sun · Siddhartha Srinivasa · Geoff Gordon
