Speaker
Luca Pesce
(EPFL)
Description
We consider the problem of generalized linear estimation on Gaussian mixture data with labels given by a single-index model. Our first result is a sharp asymptotic expression for the test and training errors in the high-dimensional regime. Motivated by the recent stream of results on the Gaussian universality of the test and training errors in generalized linear estimation, we ask ourselves the question: "when is a single Gaussian enough to characterize the error?". Our formulas allow us to give sharp answers to this question, both in the positive and negative directions.
Primary author
Luca Pesce
(EPFL)
