@phdthesis{discovery1572581,
            note = {Unpublished},
           month = {September},
          school = {UCL (University College London)},
          editor = {M Speekenbrink},
       booktitle = {University College London},
            year = {2017},
           title = {Towards a unifying theory of generalization},
        keywords = {Generalization, Function Learning, Gaussian Process, Exploration-Exploitation},
             url = {https://discovery.ucl.ac.uk/id/eprint/1572581/},
          author = {Schulz, Eric},
        abstract = {How do humans generalize from observed to unobserved data? How does generalization support inference, prediction, and decision making? I propose that a big part of human generalization can be explained by a powerful mechanism of function learning. I put forward and assess Gaussian Process regression as a model of human function learning that can unify several psychological theories of generalization. Across 14 experiments and using extensive computational modeling, I show that this model generates testable predictions about human preferences over different levels of complexity, provides a window into compositional inductive biases, and --combined with an optimistic yet efficient sampling strategy-- guides human decision making through complex spaces. Chapters 1 and 2 propose that, from a psychological and mathematical perspective, function learning and generalization are close kin. Chapter 3 derives and tests theoretical predictions of participants' preferences over differently complex functions. Chapter 4 develops a compositional theory of generalization and extensively probes this theory using 8 experimental paradigms. During the second half of the thesis, I investigate how function learning guides decision making in complex decision making tasks. In particular, Chapter 5 will look at how people search for rewards in various grid worlds where a spatial correlation of rewards provides a context supporting generalization and decision making. Chapter 6 gauges human behavior in contextual multi-armed bandit problems where a function maps features onto expected rewards. In both Chapter 5 and Chapter 6, I find that the vast majority of subjects are best predicted by a Gaussian Process function learning model combined with an upper confidence bound sampling strategy. Chapter 7 will formally assess the adaptiveness of human generalization in complex decision making tasks using mismatched Bayesian optimization simulations and finds that the empirically observed phenomenon of undergeneralization might rather be a feature than a bug of human behavior. Finally, I summarize the empirical and theoretical lessons learned and lay out a road-map for future research on generalization in Chapter 8.}
}