We derive a formula for the backward error of a complex number λ when considered as an approximate eigenvalue of a Hermitian matrix pencil or polynomial with respect to Hermitian perturbations. The same are also obtained for approximate eigenvalues of matrix pencils and polynomials with related structures like skew-Hermitian, ∗-even and ∗-odd. Numerical experiments suggest that in many cases th...

Backward simulation is an approximate inference technique for Bayesian belief networks. It differs from existing simulation methods in that it starts simulation from the known evidence and works backward (i.e., contrary to the direction of the arcs). The technique's focus on the evidence leads to improved convergence in situations where the posterior beliefs are dominated by the evidence rather...

Reverse-time de-migration (RTDM) is formulated as the adjoint operator of reverse-time migration (RTM). In acoustic medium, RTM provides a good approximation to the inverse of RTDM, and can be used to iteratively invert for the reflectivity image in least-squares RTM (LSRTM). In viscoelastic medium, however, the adjoint of the RTDM operator is far from its inverse because of amplitude attenuati...

We propose an iterative approximate reconstruction algorithm for non-overdetermined inverse scattering at fixed energy E with incomplete data in dimension d ≥ 2. In particular, we obtain rapidly converging approximate reconstructions for this inverse scattering for E → +∞.

Partially observable Markov decision processes (POMDPs) provide a principled, general framework for robot motion planning in uncertain and dynamic environments. They have been applied to various robotic tasks. However, solving POMDPs exactly is computationally intractable. A major challenge is to scale up POMDP algorithms for complex robotic tasks. Robotic systems often have mixed observability...

Estimating and tracking the state is a fundamental ability of any autonomous system. The complexity of state spaces in typical applications frequently necessitate approximate filtering techniques such as particle filters. However, these methods often suffer from the curse of dimensionality when attempting to maintain a high-dimensional joint posterior distribution. Based on the insight that mos...

Many solution methods for Markov Decision Processes (MDPs) exploit structure in the problem and are based on value function factorization. Especially multiagent settings, however, are known to suffer from an exponential increase in value component sizes as interactions become denser, restricting problem sizes and types that can be handled. We present an approach to mitigate this limitation for ...

A block tridiagonal matrix is factored with minimal fill-in using a cyclic reduction algorithm that is easily parallelized. Storage of the factored blocks allows the application of the inverse to multiple right-hand sides which may not be known at factorization time. Scalability with the number of block rows is achieved with cyclic reduction, while scalability with the block size is achieved us...

We present computational methods and subroutines to compute Gaussian quadrature integration formulas for arbitrary positive measures. For expensive integrands that can be factored into well-known forms, Gaussian quadrature schemes allow for efficient evaluation of high-accuracy and -precision numerical integrals, especially compared to general ad hoc schemes. In addition, for certain well-known...