Search Results for author: Nick Hengartner

Found 2 papers, 1 papers with code

A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks

1 code implementation21 Jan 2022 Xiaoyu Ma, Sylvain Sardy, Nick Hengartner, Nikolai Bobenko, Yen Ting Lin

To fit sparse linear associations, a LASSO sparsity inducing penalty with a single hyperparameter provably allows to recover the important features (needles) with high probability in certain regimes even if the sample size is smaller than the dimension of the input vector (haystack).

Robustness to Label Noise Depends on the Shape of the Noise Distribution in Feature Space

no code implementations2 Jun 2022 Diane Oyen, Michal Kucer, Nick Hengartner, Har Simrat Singh

However, for the special case of class-dependent label noise (independent of features given the class label), the tipping point can be as low as 50%.

Cannot find the paper you are looking for? You can Submit a new open access paper.