Distributed Online System Identification for LTI Systems Using Reverse Experience Replay
Identification of linear time-invariant (LTI) systems plays an important role in control and reinforcement learning. Both asymptotic and finite-time offline system identification are well-studied in the literature. For online system identification, the idea of stochastic-gradient descent with reverse experience replay (SGD-RER) was recently proposed, where the data sequence is stored in several buffers and the stochastic-gradient descent (SGD) update performs backward in each buffer to break the time dependency between data points. Inspired by this work, we study distributed online system identification of LTI systems over a multi-agent network. We consider agents as identical LTI systems, and the network goal is to jointly estimate the system parameters by leveraging the communication between agents. We propose DSGD-RER, a distributed variant of the SGD-RER algorithm, and theoretically characterize the improvement of the estimation error with respect to the network size. Our numerical experiments certify the reduction of estimation error as the network size grows.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
WantWords: An Open-source Online Reverse Dictionary System
A reverse dictionary takes descriptions of words as input and outputs words semantically matching the input descriptions. Reverse dictionaries have great practical value such as solving the tip-of-the-tongue problem and …
Reverse DictionaryOnline Adversarial Stabilization of Unknown Networked Systems
We investigate the problem of stabilizing an unknown networked linear system under communication constraints and adversarial disturbances. We propose the first provably stabilizing algorithm for the problem. The algorith…
Distributed Identification of Contracting and/or Monotone Network Dynamics
This paper proposes methods for identification of large-scale networked systems with guarantees that the resulting model will be contracting -- a strong form of nonlinear stability -- and/or monotone, i.e. order relation…
Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System Identification
Machine learning is becoming increasingly important for nonlinear system identification, including dynamical systems with spatially distributed outputs. However, classical identification and forecasting approaches become…
Image GenerationReverse Engineering and Security Evaluation of Commercial Tags for RFID-Based IoT Applications
The Internet of Things (IoT) is a distributed system of physical objects that requires the seamless integration of hardware (e.g., sensors, actuators, electronics) and network communications in order to collect and excha…