Search Results for author: Natalia Shepeleva

Found 2 papers, 2 papers with code

The balancing principle for parameter choice in distance-regularized domain adaptation

1 code implementation NeurIPS 2021 Werner Zellinger, Natalia Shepeleva, Marius-Constantin Dinu, Hamid Eghbal-zadeh, Hoan Nguyen, Bernhard Nessler, Sergei Pereverzyev, Bernhard A. Moser

Our approach starts with the observation that the widely-used method of minimizing the source error, penalized by a distance measure between source and target feature representations, shares characteristics with regularized ill-posed inverse problems.

Unsupervised Domain Adaptation

ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy

1 code implementation20 May 2020 Natalia Shepeleva, Werner Zellinger, Michal Lewandowski, Bernhard Moser

We propose a new metric space of ReLU activation codes equipped with a truncated Hamming distance which establishes an isometry between its elements and polyhedral bodies in the input space which have recently been shown to be strongly related to safety, robustness, and confidence.

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