Header logo is


2012


Thumb xl thumb hennigk2012
Quasi-Newton Methods: A New Direction

Hennig, P., Kiefel, M.

In Proceedings of the 29th International Conference on Machine Learning, pages: 25-32, ICML ’12, (Editors: John Langford and Joelle Pineau), Omnipress, New York, NY, USA, ICML, July 2012 (inproceedings)

Abstract
Four decades after their invention, quasi- Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.

ei ps pn

website+code pdf link (url) [BibTex]

2012


website+code pdf link (url) [BibTex]


Thumb xl screen shot 2017 09 21 at 00.54.33
Entropy Search for Information-Efficient Global Optimization

Hennig, P., Schuler, C.

Journal of Machine Learning Research, 13, pages: 1809-1837, -, June 2012 (article)

Abstract
Contemporary global optimization algorithms are based on local measures of utility, rather than a probability measure over location and value of the optimum. They thus attempt to collect low function values, not to learn about the optimum. The reason for the absence of probabilistic global optimizers is that the corresponding inference problem is intractable in several ways. This paper develops desiderata for probabilistic optimization algorithms, then presents a concrete algorithm which addresses each of the computational intractabilities with a sequence of approximations and explicitly adresses the decision problem of maximizing information gain from each evaluation.

ei pn

PDF Web Project Page [BibTex]

PDF Web Project Page [BibTex]


no image
Learning Tracking Control with Forward Models

Bócsi, B., Hennig, P., Csató, L., Peters, J.

In pages: 259 -264, IEEE International Conference on Robotics and Automation (ICRA), May 2012 (inproceedings)

Abstract
Performing task-space tracking control on redundant robot manipulators is a difficult problem. When the physical model of the robot is too complex or not available, standard methods fail and machine learning algorithms can have advantages. We propose an adaptive learning algorithm for tracking control of underactuated or non-rigid robots where the physical model of the robot is unavailable. The control method is based on the fact that forward models are relatively straightforward to learn and local inversions can be obtained via local optimization. We use sparse online Gaussian process inference to obtain a flexible probabilistic forward model and second order optimization to find the inverse mapping. Physical experiments indicate that this approach can outperform state-of-the-art tracking control algorithms in this context.

ei pn

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Approximate Gaussian Integration using Expectation Propagation

Cunningham, J., Hennig, P., Lacoste-Julien, S.

In pages: 1-11, -, January 2012 (inproceedings) Submitted

Abstract
While Gaussian probability densities are omnipresent in applied mathematics, Gaussian cumulative probabilities are hard to calculate in any but the univariate case. We offer here an empirical study of the utility of Expectation Propagation (EP) as an approximate integration method for this problem. For rectangular integration regions, the approximation is highly accurate. We also extend the derivations to the more general case of polyhedral integration regions. However, we find that in this polyhedral case, EP's answer, though often accurate, can be almost arbitrarily wrong. These unexpected results elucidate an interesting and non-obvious feature of EP not yet studied in detail, both for the problem of Gaussian probabilities and for EP more generally.

ei pn

Web [BibTex]

Web [BibTex]


no image
Kernel Topic Models

Hennig, P., Stern, D., Herbrich, R., Graepel, T.

In Fifteenth International Conference on Artificial Intelligence and Statistics, 22, pages: 511-519, JMLR Proceedings, (Editors: Lawrence, N. D. and Girolami, M.), JMLR.org, AISTATS , 2012 (inproceedings)

Abstract
Latent Dirichlet Allocation models discrete data as a mixture of discrete distributions, using Dirichlet beliefs over the mixture weights. We study a variation of this concept, in which the documents' mixture weight beliefs are replaced with squashed Gaussian distributions. This allows documents to be associated with elements of a Hilbert space, admitting kernel topic models (KTM), modelling temporal, spatial, hierarchical, social and other structure between documents. The main challenge is efficient approximate inference on the latent Gaussian. We present an approximate algorithm cast around a Laplace approximation in a transformed basis. The KTM can also be interpreted as a type of Gaussian process latent variable model, or as a topic model conditional on document features, uncovering links between earlier work in these areas.

ei pn

PDF Web [BibTex]

PDF Web [BibTex]


Thumb xl screen shot 2018 02 03 at 4.20.18 pm
Development of a Minimalistic Pneumatic Quadruped Robot for Fast Locomotion

Narioka, K., Rosendo, A., Spröwitz, A., Hosoda, K.

In Proceedings of the 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2012, pages: 307-311, IEEE, Guangzhou, 2012 (inproceedings)

Abstract
In this paper, we describe the development of the quadruped robot ”Ken” with the minimalistic and lightweight body design for achieving fast locomotion. We use McKibben pneumatic artificial muscles as actuators, providing high frequency and wide stride motion of limbs, also avoiding problems with overheating. We conducted a preliminary experiment, finding out that the robot can swing its limb over 7.5 Hz without amplitude reduction, nor heat problems. Moreover, the robot realized a several steps of bouncing gait by using simple CPG-based open loop controller, indicating that the robot can generate enough torque to kick the ground and limb contraction to avoid stumbling.

dlg

DOI [BibTex]

DOI [BibTex]


Thumb xl screen shot 2018 02 03 at 7.25.55 pm
Locomotion through Reconfiguration based on Motor Primitives for Roombots Self-Reconfigurable Modular Robots

Bonardi, S., Moeckel, R., Spröwitz, A., Vespignani, M., Ijspeert, A. J.

In Robotics; Proceedings of ROBOTIK 2012; 7th German Conference on, pages: 1-6, 2012 (inproceedings)

Abstract
We present the hardware and reconfiguration experiments for an autonomous self-reconfigurable modular robot called Roombots (RB). RB were designed to form the basis for self-reconfigurable furniture. Each RB module contains three degrees of freedom that have been carefully selected to allow a single module to reach any position on a 2-dimensional grid and to overcome concave corners in a 3-dimensional grid. For the first time we demonstrate locomotion capabilities of single RB modules through reconfiguration with real hardware. The locomotion through reconfiguration is controlled by a planner combining the well-known D* algorithm and composed motor primitives. The novelty of our approach is the use of an online running hierarchical planner closely linked to the real hardware.

dlg

link (url) [BibTex]

link (url) [BibTex]