3 papers
math.PR2026
Variational Formulas for the Spectrum of Block Wishart Matrices
Andrea Montanari, Basil Saeed
We analyze the asymptotics of a block-Wishart random matrix ensemble of the type ${\boldsymbol W}_k = ({\boldsymbol X}^* \otimes {\boldsymbol I}_k){\boldsymbol T}({\boldsymbol X}\o…
cs.LG2026
Phase Transitions for Feature Learning in Neural Networks
Andrea Montanari, Zihao Wang
According to a popular viewpoint, neural networks learn from data by first identifying low-dimensional representations, and subsequently fitting the best model in this space. Recen…
math.ST2019
Linearized two-layers neural networks in high dimension
Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz +1
We consider the problem of learning an unknown function on the -dimensional sphere with respect to the square loss, given i.i.d. samples $\{(y_i,{\boldsymbol x}_i)\}…