| Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes A Mallasto, A Feragen Advances in Neural Information Processing Systems 30, 2017 | 109 | 2017 |
| Entropy-regularized 2-Wasserstein distance between Gaussian measures A Mallasto, A Gerolin, HQ Minh Information Geometry 5 (1), 289-323, 2022 | 50 | 2022 |
| Wrapped Gaussian process regression on Riemannian manifolds A Mallasto, A Feragen The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 | 50 | 2018 |
| How well do wgans estimate the wasserstein metric? A Mallasto, G Montúfar, A Gerolin arXiv preprint arXiv:1910.03875, 2019 | 34 | 2019 |
| Probabilistic Riemannian submanifold learning with wrapped Gaussian process latent variable models A Mallasto, S Hauberg, A Feragen arXiv preprint arXiv:1805.09122, 2018 | 17 | 2018 |
| (q, p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs A Mallasto, J Frellsen, W Boomsma, A Feragen arXiv preprint arXiv:1902.03642, 2019 | 14 | 2019 |
| Entropy-Regularized -Wasserstein Distance between Gaussian Measures A Mallasto, A Gerolin, HQ Minh arXiv preprint arXiv:2006.03416, 2020 | 7 | 2020 |
| Simulation of conditioned diffusions on the flat torus MH Jensen, A Mallasto, S Sommer Geometric Science of Information: 4th International Conference, GSI 2019 …, 2019 | 6 | 2019 |
| From alexnet to transformers: Measuring the non-linearity of deep neural networks with affine optimal transport Q Bouniot, I Redko, A Mallasto, C Laclau, K Arndt, O Struckmeier, ... arXiv preprint arXiv:2310.11439, 2023 | 3 | 2023 |
| A formalization of the natural gradient method for general similarity measures A Mallasto, TD Haije, A Feragen Geometric Science of Information: 4th International Conference, GSI 2019 …, 2019 | 3 | 2019 |
| Learning representations that are closed-form Monge mapping optimal with application to domain adaptation O Struckmeier, I Redko, A Mallasto, K Arndt, M Heinonen, V Kyrki arXiv preprint arXiv:2305.07500, 2023 | 2 | 2023 |
| Bayesian inference for optimal transport with stochastic cost A Mallasto, M Heinonen, S Kaski Asian Conference on Machine Learning, 1601-1616, 2021 | 2 | 2021 |
| Affine transport for sim-to-real domain adaptation A Mallasto, K Arndt, M Heinonen, S Kaski, V Kyrki arXiv preprint arXiv:2105.11739, 2021 | 2 | 2021 |
| Estimating 2-Sinkhorn divergence between Gaussian processes from finite-dimensional marginals A Mallasto arXiv preprint arXiv:2102.03267, 2021 | 1 | 2021 |
| Understanding deep neural networks through the lens of their non-linearity Q Bouniot, I Redko, A Mallasto, C Laclau, O Struckmeier, K Arndt, ... | | 2023 |
| Beyond invariant representation learning: linearly alignable latent spaces for efficient closed-form domain adaptation. O Struckmeier, I Redko, A Mallasto, K Arndt, M Heinonen, V Kyrki CoRR, 2023 | | 2023 |
| 3.5 Geometry in uncertainty quantification A Feragen, A Mallasto, S Hauberg Visualization and Processing of Anisotropy in Imaging, Geometry, and …, 0 | | |
Aasa FeragenProfessor, DTU ComputeVerified email at dtu.dk
