Accepted Abstracts

  1. Gautier Marti, Philippe Donnat, Sébastien Andler, and  Frank Nielsen.
    "Which Geometry for Clustering Copulas?"

  2. Ming Yang and Zhipeng Wang.
    "On De Lathauwer’s block term tensor decompositions"

  3. Pengyu Xiao and Laura Balzano.
    "Sparse Orthogonal Subspace Estimation"

  4. Ke Sun and Frank Nielsen.
    "Learning on High-dimensional Neuromanifolds with Relative Natural Gradients"

  5. David M. Rosen and Luca Carlone.
    A Certifiably Exact Algorithm for Large-Scale SE(3) Synchronization"

  6. Stephen Giguere, Sridhar Mahadevan, and Sarath Chandar.
    "Optimized Subspaces for Semi-Supervised Domain Adaptation"

  7. Maruan Al-Shedivat, Yo Joong Choe, Neil Spencer, and Eric P. Xing.
    Learning Diverse Overcomplete Dictionaries via Determinantal Priors"

  8. Zachary D. Kurtz, Christian L. Müller, and Richard A. Bonneau.
    "Sparse distance metric learning for embedding compositional data"

  9. Jonas Nordhaug Myhre, Matineh Shaker, Robert Jenssen, and Deniz Erdogmus.
    "Geometric Interpretation of Density Ridge Manifold Estimation"

  10. Qinxun Bai, Steven Rosenberg, Zheng Wu, and Stan Sclaroff.  
    "A Differential Geometric Regularization Approach for Supervised Learning of Classifiers"

  11. Stephanie L. Hyland and Gunnar Rätsch.
    "Learning Unitary Operators with Help From u(n)"

  12. Jonas Nordhaug Myhre, Michael Kampffmeyer, and Robert Jenssen.
    Ambient space manifold learning using density ridges"

  13. Alessandra Tosi, Søren Hauberg, and Neil Lawrence.
    "PRIME: Probabilistic Riemannian Metrics for Generative Models"

  14. Cyril J. Stark.
    "Identifiability of matrix factorizations"

  15. Alexandre K. W. Navarro, Jes Frellsen, Richard E. Turner.
    "Regression for Circular Variables using the Multivariate Generalised von Mises Distribution"

  16. Muhammad Arjumand Masood and Finale Doshi-Velez.
    "Leveraging Geometry for Fast Mixing Bayesian Non-negative Matrix Factorization"

  17. Alexander Kuleshov and Alexander Bernstein.
    "Regression via Manifold Learning"