Convergence rates for shallow neural networks learned by gradient descent. Bernoulli, (30)1:475-502, Bernoulli Society for Mathematical Statistics and Probability, 2024. [PUMA: ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie wos]
Reproducing kernel Hilbert spaces cannot contain all continuous functions on a compact metric space. Archiv der Mathematik, (122)5:553-557, Springer, 2024. [PUMA: oa ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie wos]
Code and Data for: Better by default: Strong pre-tuned MLPs and boosted trees on tabular data. 2024. [PUMA: darus mult ubs_10008 ubs_10021 ubs_20013 ubs_20019 ubs_30126 ubs_30165 ubs_40202 unibibliografie]
Mind the spikes : benign overfitting of kernels and neural networks in fixed dimension. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems, 20763-20826, Association for Computing Machinery, 2024. [PUMA: abgleich ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie]
Sonomorphologic Changes in Colorectal Deep Endometriosis : The Long-Term Impact of Age and Hormonal Treatment. Ultraschall in der Medizin, Thieme, 2023. [PUMA: ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie wos]
Empirical Risk Minimization in the Interpolating Regime with Application to Neural Network Learning. 2019. [PUMA: sent ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie]
Classification With Repeated Observations. IEEE signal processing letters, (30):1522-1526, IEEE, 2023. [PUMA: wos ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie]
Lossless Transformations and Excess Risk Bounds in Statistical Inference. Entropy, (25)10:1394, MDPI, 2023. [PUMA: oa ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie wos]
A new regularized stochastic approximation framework for stochastic inverse problems. Nonlinear analysis-real world applications, (73)October:103869, Elsevier, 2023. [PUMA: ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie wos]
Intrinsic Dimension Adaptive Partitioning for Kernel Methods. SIAM journal on mathematics of data science, (4)2:721-749, Society for Industrial and Applied Mathematics, 2022. [PUMA: ubs_10008 ubs_20013 ubs_30126 ubs_40202 unibibliografie wos]
Radial kernels and their reproducing kernel Hilbert spaces. Journal of complexity, (26)6:641-660, Elsevier, 2010. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise. The annals of statistics, (37)2:841-875, Institute of Mathematical Statistics, 2009. [PUMA: fis liste oa ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Learning from dependent observations. Journal of multivariate analysis, (100)1:175-194, Elsevier, 2009. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Optimal rates for regularized least squares regression. 2009. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Oracle inequalities for support vector machines that are based on random entropy numbers. Journal of complexity, (25)5:437-454, Elsevier, 2009. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Sparsity of SVMs that use the epsilon-insensitive loss. In Daphne Koller, Dale Schuurmans, Yoshua Bengio, and Léon Bottou (Eds.), Advances in neural information processing systems 21 : 22nd Annual Conference on Neural Information Processing Systems 2008, (3):1569-1576, Curran Associates Inc., Red Hook, NY, 2009. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Using support vector machines for anomalous change detection. 2010 IEEE International Geoscience and Remote Sensing Symposium, (5):3732-3735, IEEE, Piscataway, NJ, 2010. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
On consistency and robustness properties of support vector machines for heavy-tailed distributions. Statistics and its interface, (2)3:311-327, International Press, 2009. [PUMA: fis liste ubs_10008 ubs_20013 ubs_30126 ubs_40202]
Fast learning from non-i.i.d. observations. In Yoshua Bengio, Dale Schuurmans, John Lafferty, Chris Williams, and Aron Culotta (Eds.), Advances in neural information processing systems 22 : 23rd Annual Conference on Neural Information Processing Systems 2009, (3):1768-1776, Curran, Red Hook, NY, 2010. [PUMA: fis liste oa ubs_10008 ubs_20013 ubs_30126 ubs_40202] URL
Two oracle inequalities for regularized boosting classifiers. Statistics and its interface, (2)3:271-284, International Press, 2009. [PUMA: fis liste oa ubs_10008 ubs_20013 ubs_30126 ubs_40202]