| Beyond the Bakushinkii veto: regularising linear inverse problems without knowing the noise distribution B Harrach, T Jahn, R Potthast Numerische Mathematik 145, 581-603, 2020 | 18 | 2020 |
| On the discrepancy principle for stochastic gradient descent T Jahn, B Jin Inverse Problems 36 (9), 095009, 2020 | 16 | 2020 |
| The sensorimotor loop as a dynamical system: how regular motion primitives may emerge from self-organized limit cycles B Sándor, T Jahn, L Martin, C Gros Frontiers in Robotics and AI 2, 31, 2015 | 14 | 2015 |
| Optimal convergence of the discrepancy principle for polynomially and exponentially ill-posed operators under white noise T Jahn Numerical Functional Analysis and Optimization 43 (2), 145-167, 2022 | 7 | 2022 |
| Regularising linear inverse problems under unknown non-Gaussian white noise B Harrach, T Jahn, R Potthast arXiv preprint arXiv:2010.04519, 2020 | 6 | 2020 |
| A modified discrepancy principle to attain optimal convergence rates under unknown noise T Jahn Inverse Problems 37 (9), 095008, 2021 | 5 | 2021 |
| Regularizing linear inverse problems under unknown non-Gaussian white noise allowing repeated measurements B Harrach, T Jahn, R Potthast IMA Journal of Numerical Analysis 43 (1), 443-500, 2023 | 4 | 2023 |
| A probabilistic oracle inequality and quantification of uncertainty of a modified discrepancy principle for statistical inverse problems T Jahn arXiv preprint arXiv:2202.12596, 2022 | 4 | 2022 |
| Noise level free regularization of general linear inverse problems under unconstrained white noise T Jahn SIAM/ASA Journal on Uncertainty Quantification 11 (2), 591-615, 2023 | 3 | 2023 |
| Discretisation-adaptive regularisation of statistical inverse problems T Jahn arXiv preprint arXiv:2204.14037, 2022 | 2 | 2022 |
| Increasing the relative smoothness of stochastically sampled data T Jahn arXiv preprint arXiv:2103.03545, 2021 | 1 | 2021 |
| Regularising linear inverse problems under unknown non-Gaussian noise TN Jahn Dissertation, Frankfurt am Main, Johann Wolfgang Goethe-Universität, 2021, 2020 | 1 | 2020 |
| Early Stopping of Untrained Convolutional Neural Networks T Jahn, B Jin arXiv preprint arXiv:2402.04610, 2024 | | 2024 |
| Efficient Solution of ill-posed integral equations through averaging M Griebel, T Jahn arXiv preprint arXiv:2401.16250, 2024 | | 2024 |
| Convergence of generalized cross-validation for an ill-posed integral equation T Jahn Institut für Numerische Simulation 2303, 2023 | | 2023 |
| Non-Bayesian regularisation of stochastically sampled data TN Jahn Функциональные пространства. Дифференциальные операторы. Проблемы …, 2018 | | 2018 |
| Dynamical states in the sensorimotor loop of a rolling robot T Jahn, L Martin, R Echeveste, C Gros Bulletin of the American Physical Society 61, 2016 | | 2016 |
| Dynamical states in the sensorimotor loop of a rolling robot B Sándor, T Jahn, L Martin, R Echeveste, C Gros APS March Meeting Abstracts 2016, Y40. 014, 2016 | | 2016 |
