Locality Regularized Reconstruction: Structured Sparsity and Delaunay Triangulations

Linear representation learning is widely studied due to its conceptual simplicity and empirical utility in tasks such as compression, classification, and feature extraction. Given a set of points [x1, x2, ldots, xn] = X ∈ ℝd × n and a vector y ∈ ℝd, the goal is to find coefficients w ∈ ℝn so that X w ≈ y, subject to some desired structure on w. In this work we seek w that forms a local reconstruction of y by solving a regularized least squares regression problem. We obtain local solutions through a locality function that promotes the use of columns of X that are close to y when used as a regularization term. We prove that, for all levels of regularization and under a mild condition that the columns of X have a unique Delaunay triangulation, the optimal coefficients' number of non-zero entries is upper bounded by d+1, thereby providing local sparse solutions when d ll n. Under the same condition we also show that for any y contained in the convex hull of X there exists a regime of regularization parameter such that the optimal coefficients are supported on the vertices of the Delaunay simplex containing y. This provides an interpretation of the sparsity as having structure obtained implicitly from the Delaunay triangulation of X. We demonstrate that our locality regularized problem can be solved in comparable time to other methods that identify the containing Delaunay simplex.