We consider conditions under which the SR1 iteration is locally convergent. We apply the result to a pointwise structured SR1 method that has been used in optimal control.

We study an estimator with a convex formulation for recovery of low-rank matrices from rank-one projections. Using initial estimates the factors target $d_1\times d_2$ matrix rank-$r$, admits practical subgradient method operating in space dimension $r(d_1+d_2)$. This property makes significantly more scalable than estimators based on lifting and semidefinite programming. Furthermore, we presen...

A recently-proposed machine learning approach to reference resolution — the twin-candidate approach — has been shown to be more promising than the traditional single-candidate approach. This paper presents a pronoun interpretation system that extends the twin-candidate framework by (1) equipping it with the ability to identify non-referential pronouns, (2) training different models for handling...

For a separable complex Hilbert space H, we say that bounded linear operator T acting on H is C-normal, where C conjugation if it satisfies CT∗TC=TT∗. normal operator, give geometric conditions which guarantee its rank-one perturbation C-normal for some C. We also obtain new properties revealing the structure of operators.

Kalman filtering-smoothing is a fundamental tool in statistical time series analysis. However, standard implementations of the Kalman filter-smoother require O(d3) time and O(d2) space per timestep, where d is the dimension of the state variable, and are therefore impractical in high-dimensional problems. In this paper we note that if a relatively small number of observations are available per ...

We consider the problem of computing square root a perturbation scaled identity matrix, , where and are matrices with . This arises in various applications, including computer vision optimization methods for machine learning. derive new formula th that involves weighted sum powers matrix is particularly attractive root, since has just one term when also class Newton iterations exploit low-rank ...

The change of the Kronecker structure a matrix pencil perturbed by another rank one has been characterized in terms homogeneous invariant factors and chains column row minimal indices initial pencils. We obtain here new characterization conjugate partitions corresponding both also define generalized Weyr characteristic an arbitrary bounds for it when is one. results improve known on problem hol...