Regularization-free estimation in trace regression with symmetric positive semidefinite matrices
This provides a simpler, tuning-free alternative for practitioners in fields like matrix completion and quantum state tomography, though it is incremental as it builds on existing regularization approaches.
The paper tackles the problem of estimating symmetric positive semidefinite matrices in trace regression, showing that simple constrained least squares without regularization can perform as well as regularization-based methods under certain design conditions, eliminating the need for tuning parameters.
Over the past few years, trace regression models have received considerable attention in the context of matrix completion, quantum state tomography, and compressed sensing. Estimation of the underlying matrix from regularization-based approaches promoting low-rankedness, notably nuclear norm regularization, have enjoyed great popularity. In the present paper, we argue that such regularization may no longer be necessary if the underlying matrix is symmetric positive semidefinite (\textsf{spd}) and the design satisfies certain conditions. In this situation, simple least squares estimation subject to an \textsf{spd} constraint may perform as well as regularization-based approaches with a proper choice of the regularization parameter, which entails knowledge of the noise level and/or tuning. By contrast, constrained least squares estimation comes without any tuning parameter and may hence be preferred due to its simplicity.