Maillard et al.'s replica prediction for Bayes risk
Consider the generalized linear model with orthogonally invariant design, and let be the posterior mean estimator. Let be a tuple in
solving the replica saddle point equations, where is the signal variance and is defined by the model. Replica Bayes-risk conjecture. There exists such a tuple for which
This conjecture predicts the asymptotic Bayes mean-squared error through the replica saddle point equations. The source later relates their solutions to Bayes-GVAMP state-evolution fixed points, but does not establish the asserted asymptotic risk formula in general.
References
- Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan and Marco Mondelli, “Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing”, arXiv:2602.09240 (2026).
Progress summary
Never refreshed
Nothing recorded yet. Refresh searches the literature and the public web for attempts on this problem, and writes the first summary here.
Solutions 0
No solutions have been posted yet.