English
Related papers

Related papers: Learning deep Koopman operators with convex stabil…

200 papers

In this paper, we provide sufficient conditions for dissipativity and local asymptotic stability of discrete-time dynamical systems parametrized by deep neural networks. We leverage the representation of neural networks as pointwise affine…

Machine Learning · Computer Science 2022-06-09 Jan Drgona , Soumya Vasisht , Aaron Tuor , Draguna Vrabie

Motivated by some applications in signal processing and machine learning, we consider two convex optimization problems where, given a cone $K$, a norm $\|\cdot\|$ and a smooth convex function $f$, we want either 1) to minimize the norm over…

Optimization and Control · Mathematics 2013-03-29 Zaid Harchaoui , Anatoli Juditsky , Arkadi Nemirovski

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Tiffany Vlaar , Timothée Pouchon , Amos Storkey

We consider the problem of covariance matrix estimation in the presence of latent variables. Under suitable conditions, it is possible to learn the marginal covariance matrix of the observed variables via a tractable convex program, where…

Machine Learning · Statistics 2011-10-17 Gui-Bo Ye , Yuanfeng Wang , Yifei Chen , Xiaohui Xie

In networked control systems, communication resource constraints often necessitate the use of \emph{sparse} control input vectors. A prototypical problem is how to ensure controllability of a linear dynamical system when only a limited…

Systems and Control · Electrical Eng. & Systems 2025-06-24 Krishna Praveen V. S. Kondapi , Chandrasekhar Sriram , Geethu Joseph , Chandra R. Murthy

We present a simple model-free control algorithm that is able to robustly learn and stabilize an unknown discrete-time linear system with full control and state feedback subject to arbitrary bounded disturbance and noise sequences. The…

Optimization and Control · Mathematics 2020-10-02 Dimitar Ho , John Doyle

This paper focuses on adaptive control of the discrete-time linear quadratic regulator (adaptive LQR). Recent literature has made significant contributions in proving non-asymptotic convergence rates, but existing approaches have a few…

Systems and Control · Electrical Eng. & Systems 2026-04-27 Peter A. Fisher , Anuradha M. Annaswamy

This paper derives conditions under which Model Predictive Control (MPC) with terminal conditions, using a data-driven surrogate model as a prediction model, asymptotically stabilizes the plant despite approximation errors. In particular,…

Systems and Control · Electrical Eng. & Systems 2026-04-13 Irene Schimperna , Lea Bold , Johannes Köhler , Karl Worthmann , Lalo Magni

This paper presents new sufficient conditions for convergence and asymptotic or exponential stability of a stochastic discrete-time system, under which the constructed Lyapunov function always decreases in expectation along the system's…

Systems and Control · Computer Science 2019-06-05 Yuzhen Qin , Ming Cao , Brian D. O. Anderson

This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server. The proposed algorithm…

Machine Learning · Computer Science 2023-08-03 Jiaojiao Zhang , Dominik Fay , Mikael Johansson

Nonlinearity plays a crucial role in deep neural networks. In this paper, we investigate the degree to which the nonlinearity of the neural network is essential. For this purpose, we employ the Koopman operator, extended dynamic mode…

Machine Learning · Computer Science 2024-07-08 Naoki Sugishita , Kayo Kinjo , Jun Ohkubo

This paper presents a data-driven approach to approximate the dynamics of a nonlinear time-varying system (NTVS) by a linear time-varying system (LTVS), which is resulted from the Koopman operator and deep neural networks. Analysis of the…

Systems and Control · Electrical Eng. & Systems 2026-03-16 Wenjian Hao , Bowen Huang , Wei Pan , Di Wu , Shaoshuai Mou

We consider the problem of zeroing an error output of a nonlinear discrete-time system in the presence of constant exogenous disturbances, subject to hard convex constraints on the input signal. The design specification is formulated as a…

Optimization and Control · Mathematics 2021-05-07 John W. Simpson-Porco

In this paper, a unified batch-online learning approach is introduced to learn a linear representation of nonlinear system dynamics using the Koopman operator. The presented system modeling approach leverages a novel incremental…

Systems and Control · Electrical Eng. & Systems 2022-12-29 Majid Mazouchi , Subramanya Nageshrao , Hamidreza Modares

In this paper, we study the problem of optimizing the stability of positive semi-Markov jump linear systems. We specifically consider the problem of tuning the coefficients of the system matrices for maximizing the exponential decay rate of…

Systems and Control · Computer Science 2020-09-22 Chengyan Zhao , Masaki Ogura , Kenji Sugimoto

The Koopman operator approach provides a powerful linear description of nonlinear dynamical systems in terms of the evolution of observables. While the operator is typically infinite-dimensional, it is crucial to develop finite-dimensional…

Dynamical Systems · Mathematics 2025-03-03 Rishikesh Yadav , Alexandre Mauroy

This paper presents a data-driven control framework for quadrotor systems that integrates a deep Koopman operator with model predictive control (DK-MPC). The deep Koopman operator is trained on sampled flight data to construct a…

Robotics · Computer Science 2025-08-20 Haitham El-Hussieny

We propose a method for efficiently incorporating constraints into a stochastic gradient Langevin framework for the training of deep neural networks. Constraints allow direct control of the parameter space of the model. Appropriately…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Timothée Pouchon , Tiffany Vlaar , Amos Storkey

Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world settings where interactions are costly or dangerous. Current…

Machine Learning · Computer Science 2022-06-29 Matthias Weissenbacher , Samarth Sinha , Animesh Garg , Yoshinobu Kawahara

We study differentially private (DP) algorithms for stochastic convex optimization: the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. (2019)…

Machine Learning · Computer Science 2020-05-12 Vitaly Feldman , Tomer Koren , Kunal Talwar