Boosting-Enabled Robust System Identification of Partially Observed LTI Systems Under Heavy-Tailed Noise
This addresses robust system identification for scenarios with non-Gaussian noise, offering practical improvements for control and signal processing applications, though it is incremental relative to prior work.
The paper tackles system identification for partially observed linear time-invariant systems under heavy-tailed noise, proposing a novel algorithm that achieves sample complexity bounds nearly matching those under sub-Gaussian noise with only second-moment requirements.
We consider the problem of system identification of partially observed linear time-invariant (LTI) systems. Given input-output data, we provide non-asymptotic guarantees for identifying the system parameters under general heavy-tailed noise processes. Unlike previous works that assume Gaussian or sub-Gaussian noise, we consider significantly broader noise distributions that are required to admit only up to the second moment. For this setting, we leverage tools from robust statistics to propose a novel system identification algorithm that exploits the idea of boosting. Despite the much weaker noise assumptions, we show that our proposed algorithm achieves sample complexity bounds that nearly match those derived under sub-Gaussian noise. In particular, we establish that our bounds retain a logarithmic dependence on the prescribed failure probability. Interestingly, we show that such bounds can be achieved by requiring just a finite fourth moment on the excitatory input process.