Matthias Seeger
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Matthias Seeger has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Krause
California Institute of Technology 1200 E California Blvd. 91125 Pasadena CA USA
1 shared publication - Bernhard Schölkopf
ETH Zurich
1 shared publication - Duy Nguyen-Tuong
Max-Planck Institute for Biological Cybernetics, Tübingen, Germany
1 shared publication - Hannes Nickisch
Philips Research (Germany)
1 shared publication - Jan Peters
Technical University of Darmstadt
1 shared publication - Niranjan Srinivas
California Institute of Technology
1 shared publication
Latest Publications
- Open Access
Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design. Moreover, by bounding the latter in terms of operator spectra, we obtain explicit sublinear regret bounds for many commonly used covariance functions. In some important cases, our bounds have surprisingly weak dependence on the dimensionality. In our experiments on real sensor data, GP-UCB compares favorably with other heuristical GP optimization approaches.
Open AccessGaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design. Moreover, by bounding the latter in terms of operator spectra, we obtain explicit sublinear regret bounds for many commonly used covariance functions. In some important cases, our bounds have surprisingly weak dependence on the dimensionality. In our experiments on real sensor data, GP-UCB compares favorably with other heuristical GP optimization approaches.
- Open Access
- 26 October 2009
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 63 (1) , 116-126
Optimization ofk‐space trajectories for compressed sensing by Bayesian experimental design
The optimization ofk‐space sampling for nonlinear sparse MRI reconstruction is phrased as a Bayesian experimental design problem. Bayesian inference is approximated by a novel relaxation to standard signal processing primitives, resulting in an efficient optimization algorithm for Cartesian and spiral trajectories. On clinical resolution brain image data from a Siemens 3T scanner, automatically optimized trajectories lead to significantly improved images, compared to standard low‐pass, equispaced, or variable density randomized designs. Insights into the nonlinear design optimization problem for MRI are given. Magn Reson Med, 2010.
- 26 October 2009
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 63 (1) , 116-126
Open AccessOptimization ofk‐space trajectories for compressed sensing by Bayesian experimental design
The optimization ofk‐space sampling for nonlinear sparse MRI reconstruction is phrased as a Bayesian experimental design problem. Bayesian inference is approximated by a novel relaxation to standard signal processing primitives, resulting in an efficient optimization algorithm for Cartesian and spiral trajectories. On clinical resolution brain image data from a Siemens 3T scanner, automatically optimized trajectories lead to significantly improved images, compared to standard low‐pass, equispaced, or variable density randomized designs. Insights into the nonlinear design optimization problem for MRI are given. Magn Reson Med, 2010.