Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Gaussian Process on the Product of Directional Manifolds (2303.06799v3)

Published 13 Mar 2023 in cs.LG

Abstract: We present a principled study on defining Gaussian processes (GPs) with inputs on the product of directional manifolds. A circular kernel is first presented according to the von Mises distribution. Based thereon, the hypertoroidal von Mises (HvM) kernel is proposed to establish GPs on hypertori with consideration of correlated circular components. The proposed HvM kernel is demonstrated with multi-output GP regression for learning vector-valued functions on hypertori using the intrinsic coregionalization model. Analytic derivatives for hyperparameter optimization are provided for runtime-critical applications. For evaluation, we synthesize a ranging-based sensor network and employ the HvM-based GPs for data-driven recursive localization. Numerical results show that the HvM-based GP achieves superior tracking accuracy compared to parametric model and GPs of conventional kernel designs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. N. Ito, S. Araki, and T. Nakatani, “Complex angular central Gaussian mixture model for directional statistics in mask-based microphone array signal processing,” in European Signal Processing Conference, Aug. 2016, pp. 1153–1157.
  2. J. Glover and L. P. Kaelbling, “Tracking the spin on a ping pong ball with the quaternion Bingham filter,” in IEEE International Conference on Robotics and Automation, June 2014, pp. 4133–4140.
  3. X. Zhe, S. Chen, and H. Yan, “Directional statistics-based deep metric learning for image classification and retrieval,” Pattern Recognition, vol. 93, pp. 113–123, 2019.
  4. H. Möls, K. Li, and U. D. Hanebeck, “Highly parallelizable plane extraction for organized point clouds using spherical convex hulls,” in IEEE International Conference on Robotics and Automation, May 2020.
  5. K. Li, F. Pfaff, and U. D. Hanebeck, “Grid-based quaternion filter for SO(3) estimation,” in European Control Conference, May 2020.
  6. ——, “Circular discrete reapproximation,” in International Conference on Information Fusion, July 2022.
  7. D. Duvenaud, “Automatic model construction with Gaussian processes,” Ph.D. dissertation, University of Cambridge, 2014.
  8. F. Lindgren, H. Rue, and J. Lindst, “An explicit link between Gaussian fields and Gaussian Markov random fields: The stochastic partial differential equation approach,” Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 73, no. 4, pp. 423–498, 2011.
  9. V. Borovitskiy, A. Terenin, P. Mostowsky et al., “Matérn Gaussian processes on Riemannian manifolds,” Advances in Neural Information Processing Systems, vol. 33, pp. 12 426–12 437, 2020.
  10. M. Hutchinson, A. Terenin, V. Borovitskiy, S. Takao, Y. Teh, and M. Deisenroth, “Vector-valued Gaussian processes on Riemannian manifolds via gauge independent projected kernels,” Advances in Neural Information Processing Systems, vol. 34, pp. 17 160–17 169, 2021.
  11. A. Feragen, F. Lauze, and S. Hauberg, “Geodesic exponential kernels: When curvature and linearity conflict,” in IEEE Conference on Computer Vision and Pattern Recognition, June 2015, pp. 3032–3042.
  12. A. Majumdar, “Gaussian processes on the support of cylindrical surfaces, with application to periodic spatio-temporal data,” Journal of Statistical Planning and Inference, vol. 153, pp. 27–41, 2014.
  13. M. Lang, O. Dunkley, and S. Hirche, “Gaussian process kernels for rotations and 6D rigid body motions,” in IEEE International Conference on Robotics and Automation, June 2014, pp. 5165–5170.
  14. R. Fisher, “Dispersion on a sphere,” Proceedings of the Royal Society of London. Series A, Mathematical and Physical Sciences, vol. 217, no. 1130, pp. 295–305, 1953.
  15. K. Li, F. Pfaff, and U. D. Hanebeck, “Progressive von Mises–Fisher filtering using isotropic sample sets for nonlinear hyperspherical estimation,” Sensors, vol. 21, no. 9, p. 2991, 2021.
  16. ——, “Nonlinear von Mises–Fisher filtering based on isotropic deterministic sampling,” in IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, Sep. 2020.
  17. I. Gilitschenski, R. Sahoo, W. Schwarting, A. Amini, S. Karaman, and D. Rus, “Deep orientation uncertainty learning based on a Bingham loss,” in International Conference on Learning Representations, Apr. 2020.
  18. K. Li, D. Frisch, B. Noack, and U. D. Hanebeck, “Geometry-driven deterministic sampling for nonlinear Bingham filtering,” in European Control Conference, Jun. 2019.
  19. K. Li, “On-manifold recursive Bayesian estimation for directional domains,” Ph.D. dissertation, Karlsruhe Institute of Technology, 2022.
  20. K. Li, F. Pfaff, and U. D. Hanebeck, “Dual quaternion sample reduction for SE(2) estimation,” in International Conference on Information Fusion, Jul. 2020.
  21. G. Kurz and U. D. Hanebeck, “Toroidal information fusion based on the bivariate von Mises distribution,” in IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, Sep. 2015, pp. 309–315.
  22. S. Bultmann, K. Li, and U. D. Hanebeck, “Stereo visual SLAM based on unscented dual quaternion filtering,” in International Conference on Information Fusion, Jul. 2019, pp. 1–8.
  23. K. Li, F. Pfaff, and U. D. Hanebeck, “Unscented dual quaternion particle filter for SE(3) estimation,” IEEE Control Systems Letters, vol. 5, no. 2, pp. 647–652, 2021.
  24. ——, “Geometry-driven stochastic modeling of SE(3) states based on dual quaternion representation,” in IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, May 2019.
  25. M. A. Alvarez, L. Rosasco, and N. D. Lawrence, “Kernels for vector-valued functions: A review,” Foundations and Trends in Machine Learning, vol. 4, no. 3, pp. 195–266, 2012.
  26. N. Boumal, B. Mishra, P.-A. Absil, and R. Sepulchre, “Manopt, a Matlab toolbox for optimization on manifolds,” Journal of Machine Learning Research, vol. 15, no. 42, pp. 1455–1459, 2014.
  27. M. Kok, J. D. Hol, and T. B. Schön, “Indoor positioning using ultrawideband and inertial measurements,” IEEE Transactions on Vehicular Technology, vol. 64, no. 4, pp. 1293–1303, 2015.
  28. Y. Oshman and P. Davidson, “Optimization of observer trajectories for bearings-only target localization,” IEEE Transactions on Aerospace and Electronic Systems, vol. 35, no. 3, pp. 892–902, 1999.
  29. F. Gustafsson, F. Gunnarsson, N. Bergman, U. Forssell, J. Jansson, R. Karlsson, and P.-J. Nordlund, “Particle filters for positioning, navigation, and tracking,” IEEE Transactions on Signal Processing, vol. 50, no. 2, pp. 425–437, 2002.
  30. M. Titsias, “Variational learning of inducing variables in sparse Gaussian processes,” in International Conference on Artificial Intelligence and Statistics, Apr. 2009, pp. 567–574.
  31. M. Cai, M. Hasanbeig, S. Xiao, A. Abate, and Z. Kan, “Modular deep reinforcement learning for continuous motion planning with temporal logic,” IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 7973–7980, 2021.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now