Carnegie Mellon University
Browse

NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings

Download (676.38 kB)
journal contribution
posted on 2015-07-01, 00:00 authored by Chinmay Hegde, Aswin C. Sankaranarayanan, Wotao Yin, Richard G. Baraniuk

We propose a novel framework for the deterministic construction of linear, near-isometric embeddingsof a finite set of data points. Given a set of training points X RN, we consider the secant set S(X) that consists of all pairwise difference vectors of X, normalized to lie on the unit sphere. We formulate an affine rank minimization problem to construct a matrix that preserves the norms of all the vectors in S(X) up to a distortion parameter . While affine rank minimization is NP-hard, we show that this problem can be relaxed to a convex formulation that can be solved using a tractable semidefinite program (SDP). In order to enable scalability of our proposed SDP to very large-scale problems, we adopt a twostage approach. First, in order to reduce compute time, we develop a novel algorithm based on the Alternating Direction Method of Multipliers (ADMM) that we call Nuclear norm minimization with Max-norm constraints (NuMax) to solve the SDP. Second, we develop a greedy, approximate version ofNuMax based on the column generation method commonly used to solve large-scale linear programs. We demonstrate that our framework is useful for a number of signal processing applications via a range of experiments on large-scale synthetic and real datasets.

History

Publisher Statement

© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Date

2015-07-01