@article{HaiderScheffer2009,
  author    = {Haider, Peter and Scheffer, Tobias},
  title     = {Bayesian clustering for email campaign detection},
  isbn      = {978-1-605-58516-1},
  year      = {2009},
  language  = {en}
}
@article{SawadeBickelvonOertzenetal.2013,
  author    = {Sawade, Christoph and Bickel, Steffen and von Oertzen, Timo and Scheffer, Tobias and Landwehr, Niels},
  title     = {Active evaluation of ranking functions based on graded relevance},
  series = {Machine learning},
  volume    = {92},
  journal   = {Machine learning},
  number    = {1},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0885-6125},
  doi       = {10.1007/s10994-013-5372-5},
  pages     = {41 -- 64},
  year      = {2013},
  abstract  = {Evaluating the quality of ranking functions is a core task in web search and other information retrieval domains. Because query distributions and item relevance change over time, ranking models often cannot be evaluated accurately on held-out training data. Instead, considerable effort is spent on manually labeling the relevance of query results for test queries in order to track ranking performance. We address the problem of estimating ranking performance as accurately as possible on a fixed labeling budget. Estimates are based on a set of most informative test queries selected by an active sampling distribution. Query labeling costs depend on the number of result items as well as item-specific attributes such as document length. We derive cost-optimal sampling distributions for the commonly used performance measures Discounted Cumulative Gain and Expected Reciprocal Rank. Experiments on web search engine data illustrate significant reductions in labeling costs.},
  language  = {en}
}
@article{LandwehrKuehnSchefferetal.2016,
  author    = {Landwehr, Niels and Kuehn, Nicolas M. and Scheffer, Tobias and Abrahamson, Norman A.},
  title     = {A Nonergodic Ground-Motion Model for California with Spatially Varying Coefficients},
  series = {Bulletin of the Seismological Society of America},
  volume    = {106},
  journal   = {Bulletin of the Seismological Society of America},
  publisher = {Seismological Society of America},
  address   = {Albany},
  issn      = {0037-1106},
  doi       = {10.1785/0120160118},
  pages     = {2574 -- 2583},
  year      = {2016},
  abstract  = {Traditional probabilistic seismic-hazard analysis as well as the estimation of ground-motion models (GMMs) is based on the ergodic assumption, which means that the distribution of ground motions over time at a given site is the same as their spatial distribution over all sites for the same magnitude, distance, and site condition. With a large increase in the number of recorded ground-motion data, there are now repeated observations at given sites and from multiple earthquakes in small regions, so that assumption can be relaxed. We use a novel approach to develop a nonergodic GMM, which is cast as a varying-coefficient model (VCM). In this model, the coefficients are allowed to vary by geographical location, which makes it possible to incorporate effects of spatially varying source, path, and site conditions. Hence, a separate set of coefficients is estimated for each source and site coordinate in the data set. The coefficients are constrained to be similar for spatially nearby locations. This is achieved by placing a Gaussian process prior on the coefficients. The amount of correlation is determined by the data. The spatial correlation structure of the model allows one to extrapolate the varying coefficients to a new location and trace the corresponding uncertainties. The approach is illustrated with the Next Generation Attenuation-West2 data set, using only Californian records. The VCM outperforms a traditionally estimated GMM in terms of generalization error and leads to a reduction in the aleatory standard deviation by similar to 40\%, which has important implications for seismic-hazard calculations. The scaling of the model with respect to its predictor variables such as magnitude and distance is physically plausible. The epistemic uncertainty associated with the predicted ground motions is small in places where events or stations are close and large where data are sparse.},
  language  = {en}
}