I will be starting as an assistant professor of CS at Rice University in Fall 2018.

For the academic year 2017-2018, I will join IBM T. Watson Research Center as a Goldstine Fellow.

Our paper is accepted in AISTATS conferences this year (Fort Lauderdale, Florida).

Abstract. We consider the non-square matrix sensing problem, under restricted isometry property (RIP) assumptions. We focus on the non-convex formulation, where any rank-$r$ matrix $X \in \mathbb{R}^{m \times n}$ is represented as $UV^\top$, where $U \in \mathbb{R}^{m \times r}$ and $V \in \mathbb{R}^{n \times r}$. In this paper, we complement recent findings on the non-convex geometry of the analogous PSD setting [5], and show that matrix factorization does not introduce any spurious local minima, under RIP.