Wishart-prior matrix generalized linear model conjecture
Let be the free entropy of the Gaussian-equivalent matrix generalized linear model, with , and let , , , and have the meanings in the model. Define
where , , and . The free entropy of a matrix generalized linear model. Assuming the limit defining is well-defined,
This extends the generalized-linear-model free-entropy formula to the dependent Wishart prior; the source identifies technical difficulties in establishing it rigorously, so it remains conjectural.
References
Primary source
Antoine Maillard, Emanuele Troiani, Simon Martin, Florent Krzakala and Lenka Zdeborová, “Bayes-optimal learning of an extensive-width neural network from quadratically many samples”, arXiv:2408.03733 (2024).
Progress summary
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.