@phdthesis{Sawade2012,
  author    = {Sawade, Christoph},
  title     = {Active evaluation of predictive models},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-255-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65583},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 157},
  year      = {2012},
  abstract  = {The field of machine learning studies algorithms that infer predictive models from data. Predictive models are applicable for many practical tasks such as spam filtering, face and handwritten digit recognition, and personalized product recommendation. In general, they are used to predict a target label for a given data instance. In order to make an informed decision about the deployment of a predictive model, it is crucial to know the model's approximate performance. To evaluate performance, a set of labeled test instances is required that is drawn from the distribution the model will be exposed to at application time. In many practical scenarios, unlabeled test instances are readily available, but the process of labeling them can be a time- and cost-intensive task and may involve a human expert. This thesis addresses the problem of evaluating a given predictive model accurately with minimal labeling effort. We study an active model evaluation process that selects certain instances of the data according to an instrumental sampling distribution and queries their labels. We derive sampling distributions that minimize estimation error with respect to different performance measures such as error rate, mean squared error, and F-measures. An analysis of the distribution that governs the estimator leads to confidence intervals, which indicate how precise the error estimation is. Labeling costs may vary across different instances depending on certain characteristics of the data. For instance, documents differ in their length, comprehensibility, and technical requirements; these attributes affect the time a human labeler needs to judge relevance or to assign topics. To address this, the sampling distribution is extended to incorporate instance-specific costs. We empirically study conditions under which the active evaluation processes are more accurate than a standard estimate that draws equally many instances from the test distribution. We also address the problem of comparing the risks of two predictive models. The standard approach would be to draw instances according to the test distribution, label the selected instances, and apply statistical tests to identify significant differences. Drawing instances according to an instrumental distribution affects the power of a statistical test. We derive a sampling procedure that maximizes test power when used to select instances, and thereby minimizes the likelihood of choosing the inferior model. Furthermore, we investigate the task of comparing several alternative models; the objective of an evaluation could be to rank the models according to the risk that they incur or to identify the model with lowest risk. An experimental study shows that the active procedure leads to higher test power than the standard test in many application domains. Finally, we study the problem of evaluating the performance of ranking functions, which are used for example for web search. In practice, ranking performance is estimated by applying a given ranking model to a representative set of test queries and manually assessing the relevance of all retrieved items for each query. We apply the concepts of active evaluation and active comparison to ranking functions and derive 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}
}
@phdthesis{GrimmSeyfarth2017,
  author    = {Grimm-Seyfarth, Annegret},
  title     = {Effects of climate change on a reptile community in arid Australia},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412655},
  school      = {Universit{\"a}t Potsdam},
  pages     = {IX, 184},
  year      = {2017},
  abstract  = {Dies ist eine kumulative Dissertation, die drei Originalstudien umfasst (eine publiziert, eine in Revision, eine eingereicht; Stand Dezember 2017). Sie untersucht, wie Reptilienarten im ariden Australien auf verschiedene klimatische Parameter verschiedener r{\"a}umlicher Skalen reagieren und analysiert dabei zwei m{\"o}gliche zugrunde liegende Hauptmechanismen: Thermoregulatorisches Verhalten und zwischenartliche Wechselwirkungen. In dieser Dissertation wurden umfassende, individuenbasierte Felddaten verschiedener trophischer Ebenen kombiniert mit ausgew{\"a}hlten Feldexperimenten, statistischen Analysen, und Vorhersagemodellen. Die hier erkannten Mechanismen und Prozesse k{\"o}nnen nun genutzt werden, um m{\"o}gliche Ver{\"a}nderungen der ariden Reptiliengesellschaft in der Zukunft vorherzusagen. Dieses Wissen wird dazu beitragen, dass unser Grundverst{\"a}ndnis {\"u}ber die Konsequenzen des globalen Wandels verbessert und Biodiversit{\"a}tsverlust in diesem anf{\"a}lligen {\"O}kosystem verhindert wird.},
  language  = {en}
}
@phdthesis{Ghahremani2024,
  author    = {Ghahremani, Sona},
  title     = {Incremental self-adaptation of dynamic architectures attaining optimality and scalability},
  doi       = {10.25932/publishup-62423},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624232},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 285},
  year      = {2024},
  abstract  = {The landscape of software self-adaptation is shaped in accordance with the need to cost-effectively achieve and maintain (software) quality at runtime and in the face of dynamic operation conditions. Optimization-based solutions perform an exhaustive search in the adaptation space, thus they may provide quality guarantees. However, these solutions render the attainment of optimal adaptation plans time-intensive, thereby hindering scalability. Conversely, deterministic rule-based solutions yield only sub-optimal adaptation decisions, as they are typically bound by design-time assumptions, yet they offer efficient processing and implementation, readability, expressivity of individual rules supporting early verification. Addressing the quality-cost trade-of requires solutions that simultaneously exhibit the scalability and cost-efficiency of rulebased policy formalism and the optimality of optimization-based policy formalism as explicit artifacts for adaptation. Utility functions, i.e., high-level specifications that capture system objectives, support the explicit treatment of quality-cost trade-off. Nevertheless, non-linearities, complex dynamic architectures, black-box models, and runtime uncertainty that makes the prior knowledge obsolete are a few of the sources of uncertainty and subjectivity that render the elicitation of utility non-trivial. This thesis proposes a twofold solution for incremental self-adaptation of dynamic architectures. First, we introduce Venus, a solution that combines in its design a ruleand an optimization-based formalism enabling optimal and scalable adaptation of dynamic architectures. Venus incorporates rule-like constructs and relies on utility theory for decision-making. Using a graph-based representation of the architecture, Venus captures rules as graph patterns that represent architectural fragments, thus enabling runtime extensibility and, in turn, support for dynamic architectures; the architecture is evaluated by assigning utility values to fragments; pattern-based definition of rules and utility enables incremental computation of changes on the utility that result from rule executions, rather than evaluating the complete architecture, which supports scalability. Second, we introduce HypeZon, a hybrid solution for runtime coordination of multiple off-the-shelf adaptation policies, which typically offer only partial satisfaction of the quality and cost requirements. Realized based on meta-self-aware architectures, HypeZon complements Venus by re-using existing policies at runtime for balancing the quality-cost trade-off. The twofold solution of this thesis is integrated in an adaptation engine that leverages state- and event-based principles for incremental execution, therefore, is scalable for large and dynamic software architectures with growing size and complexity. The utility elicitation challenge is resolved by defining a methodology to train utility-change prediction models. The thesis addresses the quality-cost trade-off in adaptation of dynamic software architectures via design-time combination (Venus) and runtime coordination (HypeZon) of rule- and optimization-based policy formalisms, while offering supporting mechanisms for optimal, cost-effective, scalable, and robust adaptation. The solutions are evaluated according to a methodology that is obtained based on our systematic literature review of evaluation in self-healing systems; the applicability and effectiveness of the contributions are demonstrated to go beyond the state-of-the-art in coverage of a wide spectrum of the problem space for software self-adaptation.},
  language  = {en}
}