We study the problem of learning a combination (e.g. a portfolio) of time series that has large autocorrelation. This is a challenging task as it involves the lag-1 autocovariance matrix of the series, which is difficult to estimate in practice. To address this issue we develop regularized versions of the autocorrelation function based on a robust optimization formulation of the problem. We hig...

In this paper, we introduce a new class of robust autocorrelation estimators based on interpreting the sample autocorrelation function as a linear regression. We investigate the efficiency and robustness properties of the estimators that result from employing three common robust regression techniques. Construction of robust autocovariance and positive definite autocorrelation estimates is discu...

Eye gaze detection under challenging lighting conditions is a non-trivial task. Pixel intensity and the shades around the eye region may change depending on the time of day, location, or due to artificial lighting. This paper introduces a lighting-adaptive solution for robust eye gaze detection. First, we propose a binarization and cropping technique to limit our region of interest. Then we dev...

We develop a framework within which robust models of preferences are computationally efficiently estimated using quadratic optimization methods. Within this framework general highly non-linear models can be computationally efficiently estimated while at the same time avoiding overfitting problems that such models typically have. We compare these models with standard logistic regression and rece...

In this work, we describe an implementation of the variational method proposed by Brox et al. in 2004, which yields accurate optical flows with low running times. It has several benefits with respect to the method of Horn and Schunck: it is more robust to the presence of outliers, produces piecewise-smooth flow fields and can cope with constant brightness changes. This method relies on the brig...

This paper considers the design of robust, nite-horizon and innnite-horizon H 2 estima-tors based on multliplier theory (which is intimately related to the mixed structured singular value). Speciically, the Popov-Tsypkin multiplier is used to develop a novel upper bound on a nite-horizon, cost function for the assumed uncertainty set. The results are then applied to develop design equations for...

Interest in robust detection and estimation in the presence of lying nodes has assumed importance in a number of applications. In this paper we motivate the robust detection problem using recent results for cooperative sensing in Cognitive Radios. Issues in robust estimation are motivated by the problem of deploying a sensor network for tracking vehicles. As a first step, we formulate an abstra...

We propose two new jump robust estimators of integrated variance based on high-frequency return observations. These MinRV and MedRV estimators provide a compelling alternative to the prevailing bi-power and multi-power variation measures. Specifically, the MedRV estimator has better theoretical efficiency properties than the tri-power variation measure and displays better finite-sample robustne...

We study the problem of estimating the position and orientation of a calibrated camera from an image of a known scene. A common problem in camera pose estimation is the existence of false correspondences between image features and modeled 3D points. Existing techniques such as ransac to handle outliers have no guarantee of optimality. In contrast, we work with a natural extension of the L∞ norm...