Preprint news

9. November 2020 /

Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension

2020

László Györfi, Harro Walk, Nearest neighbor based conformal prediction, 2020. (Verfügbar unter) Stuttgarter Mathematische Berichte 2020-002.

Thomas Berrett, László Györfi, Harro Walk, Strongly universally consistent nonparametric regression and classification with privatised data, 2020 http://arxiv.org/abs/2011.00216

David Holzmüller, On the Universality of the Double Descent Peak in Ridgeless Regression, 2020 arxiv.org

Daniel F. B. Haeufle, Isabell Wochner, David Holzmüller, Danny Driess, Michael Günther, Syn Schmitt, Muscles Reduce Neuronal Information Load: Quantification of Control Effort in Biological vs. Robotic Pointing and Walking, 2020 https://www.frontiersin.org/articles/10.3389/frobt.2020.00077/full

Thomas Hamm, Ingo Steinwart, Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension, 2020 arxiv.org

Ingo Steinwart, Reproducing Kernel Hilbert Spaces Cannot Contain all Continuous Functions on a Compact Metric Space, 2020 arXiv.org

David Holzmüller, Ingo Steinwart, Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent, 2020 arXiv.org

Simon Fischer, Some new bounds on the entropy numbers of diagonal operators, J. Approx. Theory, 2020.  https://doi.org/10.1016/j.jat.2019.105343

2019

Alina Braun, Michael Kohler, Harro Walk, On the rate of convergence of a neural network regression estimate learned by gradient descent, 2019. (Verfügbar unter) Stuttgarter Mathematische Berichte 2019-003.

Ingo Steinwart, Simon Fischer, A closer look at covering number bounds for Gaussian kernels, 2019, http://arxiv.org/abs/1912.11741v1 accepted in: Journal of Complexity

Simon Fischer and Ingo Steinwart, Sobolev norm learning rates for regularized least-squares algorithms, arXiv e-prints, 2019 https://arxiv.org/abs/1702.07254v2 accepted in: Journal of Machine Learning Research

Uta Freiberg und Stefan Kohl, Martin boundary theory on inhomogenous fractals, 2019 https://arxiv.org/abs/1907.07499

Ernesto De Vito, Nicole Mücke and Lorenzo Rosasco, Reproducing kernel Hilbert spaces on manifolds: Sobolev and Diffusion spaces https://arxiv.org/pdf/1905.10913.pdf

Nicole Mücke and Ingo Steinwart, Global Minima of DNNs: The lenty Pantry https://arxiv.org/pdf/1905.10686.pdf

Gilles Blanchard, Peter Mathe and Nicole Mücke, Lepskii Principle in Supervised Learning https://arxiv.org/pdf/1905.10764.pdf

I. Blaschzyk, I. Steinwart, Improved Classification Rates for Localized SVMs, arXiv:1905.01502 (2019) . [ preprint.pdf ]

I. Steinwart, A sober look at neural network initializations, tech. rep., Fakultät für Mathematik und Physik, Universität Stuttgart, 2019. [ preprint.pdf ]

Zum Seitenanfang