no code implementations • 20 Jul 2022 • Kabir Aladin Chandrasekher, Mengqi Lou, Ashwin Pananjady
Considering two prototypical choices for the nonlinearity, we study the convergence properties of a natural alternating update rule for this nonconvex optimization problem starting from a random initialization.
1 code implementation • 20 Sep 2021 • Kabir Aladin Chandrasekher, Ashwin Pananjady, Christos Thrampoulidis
In particular, provided each iteration can be written as the solution to a convex optimization problem satisfying some natural conditions, we leverage Gaussian comparison theorems to derive a deterministic sequence that provides sharp upper and lower bounds on the error of the algorithm with sample-splitting.
no code implementations • 24 Jan 2020 • Kabir Aladin Chandrasekher, Ahmed El Alaoui, Andrea Montanari
We study high-dimensional regression with missing entries in the covariates.