Optimization Letters Control and Optimization

Nonnegative low-rank matrix recovery can have spurious local minima

Richard Y. Zhang
Springer Nature · 2026-03-23 · DOI 10.1007/s11590-026-02290-0

Abstract

Abstract Low-rank matrix recovery is well-known to exhibit benign nonconvexity under the restricted isometry property (RIP): every second-order critical point is globally optimal, so local methods provably recover the ground truth. Motivated by the strong empirical performance of projected gradient methods for nonnegative low-rank recovery problems, we investigate whether this benign geometry persists when the factor matrices are constrained to be elementwise nonnegative. In the simple setting of a rank-1 nonnegative ground truth, we confirm that benign nonconvexity holds in the fully-observed case with RIP constant $$\delta =0$$ . This benign nonconvexity, however, is unstable. It fails to extend to the partially-observed case with any arbitrarily small RIP constant $$\delta >0$$ , and to higher-rank ground truths $$r^{\star }>1$$ , regardless of how much the search rank $$r\ge r^{\star }$$ is overparameterized. Together, these results undermine the standard stability-based explanation for the empirical success of nonconvex methods and suggest that fundamentally different tools are needed to analyze nonnegative low-rank recovery.

Read at publisher →