Search Results for author: Jonathan Svirsky

Found 4 papers, 2 papers with code

Single Independent Component Recovery and Applications

no code implementations12 Oct 2021 Uri Shaham, Jonathan Svirsky, Ori Katz, Ronen Talmon

Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science.

Image Generation

Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Features

1 code implementation11 Oct 2021 Uri Shaham, Ofir Lindenbaum, Jonathan Svirsky, Yuval Kluger

Experimenting on several real-world datasets, we demonstrate that our proposed approach outperforms similar approaches designed to avoid only correlated or nuisance features, but not both.

Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities

no code implementations15 Nov 2020 Uri Shaham, Igal Zaidman, Jonathan Svirsky

We empirically analyze the different components of our proposed approach and demonstrate their contribution to the performance of the model.

Age And Gender Classification

Differentiable Unsupervised Feature Selection based on a Gated Laplacian

1 code implementation NeurIPS 2021 Ofir Lindenbaum, Uri Shaham, Jonathan Svirsky, Erez Peterfreund, Yuval Kluger

In this paper, we present a method for unsupervised feature selection, and we demonstrate its use for the task of clustering.

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