Fast and Sample-Efficient Federated Low Rank Matrix Recovery from column-wise Linear and Quadratic Projections

Seyedehsara, Nayer, Namrata Vaswani

We study the following lesser-known low rank (LR) recovery problem: recover an $n\times q$ rank-$r$ matrix, $X^{\ast }=[x_1^{\ast },x_2^{\ast },...,x_q^{\ast }]$, with $r\ll \min (n,q)$, from $m$ in…