Learning deep models: Critical points and local openness

M Nouiehed, M Razaviyayn - INFORMS Journal on …, 2022 - pubsonline.informs.org
With the increasing popularity of nonconvex deep models, develo** a unifying theory for
studying the optimization problems that arise from training these models becomes very …

Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators

Y Pan, Q Zhu - arxiv preprint arxiv:2405.17370, 2024 - arxiv.org
Meta-learning has been proposed as a promising machine learning topic in recent years,
with important applications to image classification, robotics, computer games, and control …

Meta-learning guarantees for online receding horizon learning control

D Muthirayan, PP Khargonekar - arxiv preprint arxiv:2010.11327, 2020 - arxiv.org
In this paper we provide provable regret guarantees for an online meta-learning receding
horizon control algorithm in an iterative control setting. We consider the setting where, in …

Adaptive gradient online control

D Muthirayan, J Yuan… - 2022 American Control …, 2022 - ieeexplore.ieee.org
In this work we consider the online control of a known linear dynamic system with
adversarial disturbance and adversarial controller cost. The goal in online control is to …

A Meta-Learning Control Algorithm with Provable Finite-Time Guarantees

D Muthirayan, P Khargonekar - arxiv preprint arxiv:2008.13265, 2020 - arxiv.org
In this work we provide provable regret guarantees for an online meta-learning control
algorithm in an iterative control setting, where in each iteration the system to be controlled is …

[CITÁCIA][C] Regret guarantees for online receding horizon control

D Muthirayan, J Yuan, PP Khargonekar - arxiv preprint arxiv:2010.07269, 2020