Subspace estimation from unbalanced and incomplete data matrices: L_2,∞ statistical guarantees

This paper is concerned with estimating the column space of an unknown low-rank matrix A* ∈ R^d1×^d2, given noisy and partial observations of its entries. There is no shortage of scenarios where the observations-while being too noisy to support faithful recovery of the entire matrix-still convey sufficient information to enable reliable estimation of the column space of interest. This is particularly evident and crucial for the highly unbalanced case where the column dimension d₂ far exceeds the row dimension d₁, which is the focal point of the current paper. We investigate an efficient spectral method, which operates upon the sample Gram matrix with diagonal deletion. While this algorithmic idea has been studied before, we establish new statistical guarantees for this method in terms of both l₂ and l_2,∞ estimation accuracy, which improve upon prior results if d₂ is substantially larger than d₁. To illustrate the effectiveness of our findings, we derive matching minimax lower bounds with respect to the noise levels, and develop consequences of our general theory for three applications of practical importance: (1) tensor completion from noisy data, (2) covariance estimation/principal component analysis with missing data and (3) community recovery in bipartite graphs. Our theory leads to improved performance guarantees for all three cases.