Minimal Order Recovery through Rank-adaptive Identification
By: Frédéric Zheng, Yassir Jedra, Alexandre Proutière
Potential Business Impact:
Finds hidden patterns in messy data.
This paper addresses the problem of identifying linear systems from noisy input-output trajectories. We introduce Thresholded Ho-Kalman, an algorithm that leverages a rank-adaptive procedure to estimate a Hankel-like matrix associated with the system. This approach optimally balances the trade-off between accurately inferring key singular values and minimizing approximation errors for the rest. We establish finite-sample Frobenius norm error bounds for the estimated Hankel matrix. Our algorithm further recovers both the system order and its Markov parameters, and we provide upper bounds for the sample complexity required to identify the system order and finite-time error bounds for estimating the Markov parameters. Interestingly, these bounds match those achieved by state-of-the-art algorithms that assume prior knowledge of the system order.
Similar Papers
Bridging Batch and Streaming Estimations to System Identification under Adversarial Attacks
Optimization and Control
Protects machines from sneaky attacks.
A finite-sample bound for identifying partially observed linear switched systems from a single trajectory
Machine Learning (CS)
Makes computers learn how machines work better.
System Identification from Partial Observations under Adversarial Attacks
Optimization and Control
Protects computer systems from sneaky attacks.