Skip to yearly menu bar Skip to main content


Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing

Ramji Venkataramanan · Kevin K√∂gler · Marco Mondelli

Hall E #1414

Keywords: [ T: Learning Theory ] [ T: Probabilistic Methods ] [ PM: Graphical Models ] [ PM: Spectral Methods ] [ T: Optimization ]


We consider the problem of signal estimation in generalized linear models defined via rotationally invariant design matrices. Since these matrices can have an arbitrary spectral distribution, this model is well suited for capturing complex correlation structures which often arise in applications. We propose a novel family of approximate message passing (AMP) algorithms for signal estimation, and rigorously characterize their performance in the high-dimensional limit via a state evolution recursion. Our rotationally invariant AMP has complexity of the same order as the existing AMP derived under the restrictive assumption of a Gaussian design; our algorithm also recovers this existing AMP as a special case. Numerical results showcase a performance close to Vector AMP (which is conjectured to be Bayes-optimal in some settings), but obtained with a much lower complexity, as the proposed algorithm does not require a computationally expensive singular value decomposition.

Chat is not available.