| Consensus-based optimization methods converge globally in mean-field law M Fornasier, T Klock, K Riedl arXiv preprint arXiv:2103.15130, 2021 | 43* | 2021 |
| A deep network construction that adapts to intrinsic dimensionality beyond the domain A Cloninger, T Klock Neural Networks 141, 404-419, 2021 | 41* | 2021 |
| Convergence of anisotropic consensus-based optimization in mean-field law M Fornasier, T Klock, K Riedl International Conference on the Applications of Evolutionary Computation …, 2022 | 27 | 2022 |
| Managing the microvibration impact on satellite performances F Steier, T Runte, A Monsky, T Klock, G Laduree Acta Astronautica 162, 461-468, 2019 | 20 | 2019 |
| Robust and resource-efficient identification of two hidden layer neural networks M Fornasier, T Klock, M Rauchensteiner Constructive Approximation, 1-62, 2019 | 19 | 2019 |
| Adaptive multi-penalty regularization based on a generalized lasso path M Grasmair, T Klock, V Naumova Applied and Computational Harmonic Analysis 49 (1), 30-55, 2020 | 10 | 2020 |
| Stable recovery of entangled weights: Towards robust identification of deep neural networks from minimal samples C Fiedler, M Fornasier, T Klock, M Rauchensteiner Applied and Computational Harmonic Analysis 62, 123-172, 2023 | 9 | 2023 |
| Estimating covariance and precision matrices along subspaces Ž Kereta, T Klock Electronic Journal of Statistics 15 (1), 554-588, 2021 | 9 | 2021 |
| Gradient is all you need? K Riedl, T Klock, C Geldhauser, M Fornasier arXiv preprint arXiv:2306.09778, 2023 | 8 | 2023 |
| Landscape analysis of an improved power method for tensor decomposition J Kileel, T Klock, J M Pereira Advances in Neural Information Processing Systems 34, 6253-6265, 2021 | 8 | 2021 |
| Estimating multi-index models with response-conditional least squares T Klock, A Lanteri, S Vigogna Electronic Journal of Statistics 15 (1), 589-629, 2021 | 8 | 2021 |
| A level set toolbox including reinitialization and mass correction algorithms for FEniCS M Jahn, T Klock Universität, 2016 | 7 | 2016 |
| Semi-supervised manifold learning with complexity decoupled chart autoencoders SC Schonsheck, S Mahan, T Klock, A Cloninger, R Lai arXiv preprint arXiv:2208.10570, 2022 | 5 | 2022 |
| Finite Sample Identification of Wide Shallow Neural Networks with Biases M Fornasier, T Klock, M Mondelli, M Rauchensteiner arXiv preprint arXiv:2211.04589, 2022 | 4 | 2022 |
| Numerical solution of the Stefan problem in level set formulation with the eXtended finite element method in FEniCS M Jahn, T Klock Universität, 2017 | 4 | 2017 |
| Nonlinear generalization of the monotone single index model Ž Kereta, T Klock, V Naumova Information and Inference: A Journal of the IMA 10 (3), 987-1029, 2021 | 3 | 2021 |
| How Consensus-Based Optimization can be Interpreted as a Stochastic Relaxation of Gradient Descent K Riedl, T Klock, C Geldhauser, M Fornasier ICML 2024 Workshop on Differentiable Almost Everything: Differentiable …, 2024 | 1 | 2024 |
| Zentrum für technomathematik M Jahn, A Schmidt, E Bänsch Berichte aus der Technomathematik 16 (01), 2016 | 1 | 2016 |
| Chapter 6 Digital tracing, validation, and reporting A Elmokashfi, S Funke, T Klock, M Kuchta, V Naumova, J Uv Smittestopp− A Case Study on Digital Contact Tracing, 99-120, 2022 | | 2022 |
| Levelset methods (and XFEM) in FEniCS M Jahn, T Klock, A Luttmann | | |
Massimo FornasierProfessor of Applied Numerical Analysis, Technical University of Munich在 ma.tum.de 的电子邮件经过验证
