Konstantin Donhauser

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 20

Top Topics

High Dimensions

Image Interpolation

Top Venues

Publications

Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang
Certified private data release for sparse Lipschitz functions. AISTATS (2024)
Konstantin Donhauser, Javier Abad, Neha Hulkund, Fanny Yang
Privacy-preserving data release leveraging optimal transport and particle gradient descent. CoRR (2024)
Piersilvio De Bartolomeis, Javier Abad, Konstantin Donhauser, Fanny Yang
Detecting critical treatment effect bias in small subgroups. CoRR (2024)
Javier Abad, Konstantin Donhauser, Francesco Pinto, Fanny Yang
Strong Copyright Protection for Language Models via Adaptive Model Fusion. CoRR (2024)
Piersilvio De Bartolomeis, Javier Abad Martinez, Konstantin Donhauser, Fanny Yang
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials. AISTATS (2024)
Stefan Stojanovic, Konstantin Donhauser, Fanny Yang
-margin classifiers. ALT (2024)
Michael Aerni, Marco Milanta, Konstantin Donhauser, Fanny Yang
Strong inductive biases provably prevent harmless interpolation. CoRR (2023)
Konstantin Donhauser, Johan Lokna, Amartya Sanyal, March Boedihardjo, Robert Hönig, Fanny Yang
Sample-efficient private data release for Lipschitz functions under sparsity assumptions. CoRR (2023)
Michael Aerni, Marco Milanta, Konstantin Donhauser, Fanny Yang
Strong inductive biases provably prevent harmless interpolation. ICLR (2023)
Piersilvio De Bartolomeis, Javier Abad, Konstantin Donhauser, Fanny Yang
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials. CoRR (2023)
Konstantin Donhauser, Nicolò Ruggeri, Stefan Stojanovic, Fanny Yang
Fast rates for noisy interpolation require rethinking the effect of inductive bias. ICML (2022)
Konstantin Donhauser, Nicolò Ruggeri, Stefan Stojanovic, Fanny Yang
Fast rates for noisy interpolation require rethinking the effects of inductive bias. CoRR (2022)
Stefan Stojanovic, Konstantin Donhauser, Fanny Yang
-margin classifiers. CoRR (2022)
Guillaume Wang, Konstantin Donhauser, Fanny Yang
-norm interpolation of noisy data. AISTATS (2022)
Konstantin Donhauser, Alexandru Tifrea, Michael Aerni, Reinhard Heckel, Fanny Yang
Interpolation can hurt robust generalization even when there is no noise. CoRR (2021)
Konstantin Donhauser, Mingqi Wu, Fanny Yang
How rotational invariance of common kernels prevents generalization in high dimensions. CoRR (2021)
Konstantin Donhauser, Alexandru Tifrea, Michael Aerni, Reinhard Heckel, Fanny Yang
Interpolation can hurt robust generalization even when there is no noise. NeurIPS (2021)
Guillaume Wang, Konstantin Donhauser, Fanny Yang
Tight bounds for minimum l1-norm interpolation of noisy data. CoRR (2021)
Konstantin Donhauser, Mingqi Wu, Fanny Yang
How rotational invariance of common kernels prevents generalization in high dimensions. ICML (2021)
Thomas Ziegler, Manuel Fritsche, Lorenz Kuhn, Konstantin Donhauser
Efficient Smoothing of Dilated Convolutions for Image Segmentation. CoRR (2019)