System Identification Under Bounded Noise: Optimal Rates Beyond Least Squares

System identification is a fundamental problem in control and learning, particularly in high-stakes applications where data efficiency is critical. Classical approaches, such as the ordinary least squares estimator (OLS), achieve an O(1/√T) convergence rate under Gaussian noise assumptions, where T is the number of samples. This rate has been shown to match the lower bound. However, in many practical scenarios, noise is known to be bounded, opening the possibility of improving sample complexity. In this work, we establish the minimax lower bound for system identification under bounded noise, proving that the O(1/T) convergence rate is indeed optimal. We further demonstrate that OLS remains limited to an Omega(1/√T) convergence rate, making it fundamentally suboptimal in the presence of bounded noise. Finally, we instantiate two natural variations of OLS that obtain the optimal sample complexity.