Publications

Under Review

  • A. Khaleghi and S. Grünewälder, “Approximations of the Restless Bandit Problem.” [pdf]
  • S. Page and S. Grünewälder, “Ivanov-Regularised Least-Squares Estimators over Large RKHSs and Their Interpolation Spaces.” [pdf]
  • C. Pike-Burke, S. Agrawal, C. Szepesvári and S. Grünewälder, “Bandits with Delayed Anonymous Feedback.” [pdf]

Conference & Journal Publications

  • S. Grünewälder, “Compact Convex Projections”, in Journal of Machine Learning Research, 2018. [pdf]
  • S. Grünewälder, “Plug-in Estimators for Conditional Expectations and Probabilities”, in Artificial Intelligence and Statistics (AISTATS), 2018. [pdf]
  • C. Pike-Burke and S. Grünewälder, “Optimistic Planning for the Stochastic Knapsack Problem,” in Artificial Intelligence and Statistics (AISTATS), 2017.
  • F. Broekhuis, S. Grünewälder, J. McNutt, and D. W. Macdonald, “Optimal hunting conditions drive circalunar behavior of a diurnal canivore,” Behavioral Ecology, 2014.
  • S. Grünewälder, A. Gretton, and J. Shawe-Taylor, “Smooth operators,” in International Conference on Machine Learning (ICML), 2013.
  • W. Böhmer, S. Grünewälder, Y. Shen, M. Musial, and K. Obermayer, “Construction ofapproximation spaces for reinforcement learning,” Journal of Machine Learning Research, 2013.
  • S. Grünewälder*, G. Lever*, L. Baldassarre, M. Pontil, and A. Gretton, “Modelling transition dynamics in mdps with rkhs embeddings,” in International Conference on Machine Learning (ICML), 2012.
  • S. Grünewälder*, G. Lever*, A. Gretton, L. Baldassarre, S. Patterson, and M. Pontil, “Conditional mean embeddings as regressors,” in International Conference on Machine Learning (ICML), 2012.
  • W. Böhmer, S. Grünewälder, H. Nickisch, and K. Obermayer, “Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis,” Machine Learning (special issue for best ECML papers), 2012.
  • S. Grünewälder, F. Broekhuis, D. Macdonald, A. Wilson, J. McNutt, J. Shawe-Taylor, and S.Hailes, “Movement activity based classification of animal behaviour with an application to data from cheetah (Acinonyx jubatus),” In PLoS One, 2012.
  • S. Grünewälder and K. Obermayer, “The optimal unbiased value estimator and its relation to LSTD, TD and MC,” Machine Learning, 2011.
  • W. Böhmer, S. Grünewälder, H. Nickisch, and K. Obermayer, “Regularized sparse kernel slow feature analysis,” in European Conference on Machine Learning (ECML), 2011.
  • S. Grünewälder, J.-Y. Audibert, M. Opper, and J. Shawe-Taylor, “Regret bounds for gaussian process bandit problems,” in Artificial Intelligence and Statistics (AISTATS), 2010.
  • A. Onken, S. Grünewälder, M. Munk, and K. Obermayer, “Analyzing short-term noise dependencies of spike-counts in macaque prefrontal cortex using copulas and the flashlight transformation,” PLoS Computational Biology, 2009.
  • A. Onken, S. Grünewälder, and K. Obermayer, “Correlation coefficients are insufficient for analyzing spike count dependencies,” in Advances in Neural Information Processing Systems (NIPS), 2009.
  • A. Onken, S. Grünewälder, M. Munk, and K. Obermayer, “Modeling short-term noisedependence of spike counts in macaque prefrontal cortex,” in Advances in Neural Information Processing Systems (NIPS), 2008.
  • S. Grünewälder, S. Hochreiter, and K. Obermayer, “Optimality of LSTD and its relation to MC,” in International Joint Conference on Neural Networks, 2007.
  • S. Grünewälder and K. Obermayer, “Attention driven memory,” in Annual Conference of the Cognitive Science Society, 2005.