Search

The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we study domain generalization as a problem of functional regression. Our concept leads to a new algorithm for learning a linear operator from marginal distributions of inputs to the corresponding conditional distributions of outputs given inputs. Our algorithm allows a source distribution-dependent construction of reproducing kernel Hilbert spaces for prediction, and, satisfies finite sample error bounds for the idealized risk. Numerical implementations and source code are available1. [ABSTRACT FROM AUTHOR]

Estimating the ratio of two probability densities from finitely many observations of the densities is a central problem in machine learning and statistics with applications in two-sample testing, divergence estimation, generative modeling, covariate shift adaptation, conditional density estimation, and novelty detection. In this work, we analyze a large class of density ratio estimation methods that minimize a regularized Bregman divergence between the true density ratio and a model in a reproducing kernel Hilbert space (RKHS). We derive new finite-sample error bounds, and we propose a Lepskii type parameter choice principle that minimizes the bounds without knowledge of the regularity of the density ratio. In the special case of square loss, our method adaptively achieves a minimax optimal error rate. A numerical illustration is provided. [ABSTRACT FROM AUTHOR]

Multivariate calibration models often fail to extrapolate beyond the calibration samples because of changes associated with the instrumental response, environmental condition, or sample matrix. Most of the current methods used to adapt a source calibration model to a target domain exclusively apply to calibration transfer between similar analytical devices, while generic methods for calibrationmodel adaptation are largely missing. To fill this gap, we here introduce domain-invariant partial-least-squares (di-PLS) regression, which extends ordinary PLS by a domain regularizer in order to align the source and target distributions in the latent-variable space. We show that a domain-invariant weight vector can be derived in closed form, which allows the integration of (partially) labeled data from the source and target domains as well as entirely unlabeled data from the latter. We test our approach on a simulated data set where the aim is to desensitize a source calibration model to an unknown interfering agent in the target domain (i.e., unsupervised model adaptation). In addition, we demonstrate unsupervised, semisupervised, and supervised model adaptation by di-PLS on two real-world near-infrared (NIR) spectroscopic data sets. [ABSTRACT FROM AUTHOR]

Abstract Stereoscopic images and videos can lead to serious adverse effects on human visual perception. The phenomenon of visual discomfort depends on various influencing factors such as the arrangement of the display system, the image quality and the design of 3D effects. Real-time depth adaptations that reduce the extent of visual discomfort require computationally efficient prediction models. This article analyzes optimal combinations of image features of state-of-the-art models in terms of prediction accuracy and computational efficiency. In addition, a fast-to-compute disparity contrast feature based on Haralick contrast is introduced in this context. It turns out that the computational complexity can be reduced by restricting the number of features without loss of prediction accuracy. A Pareto-front analysis shows which features are more likely to be part of optimal combinations. It is interesting to observe that the introduced disparity contrast feature is part of combinations that are optimal in terms of both computational efficiency and accuracy. This means that state-of-the-art prediction models can be improved by means of the introduced disparity contrast feature. The analysis relies on statistical evaluations based on publicly available assessment data. [ABSTRACT FROM AUTHOR]