Krzakala et al.'s TAP prediction for the free energy of Bayes linear regression
Let β=(β1,…,βp)\beta=(\beta_1,\ldots,\beta_p)β=(β1,…,βp) have product prior π0=π⊗p\pi_0=\pi^{\otimes p}π0=π⊗p, where π\piπ is a probability distribution on [−1,1][-1,1][−1,1]. Let Zp\mathcal{Z}_pZp denote the linear-regres…