Search Results for author: John Kalantari

Found 5 papers, 1 papers with code

Universally Rank Consistent Ordinal Regression in Neural Networks

2 code implementations14 Oct 2021 Garrett Jenkinson, Gavin R. Oliver, Kia Khezeli, John Kalantari, Eric W. Klee

Despite the pervasiveness of ordinal labels in supervised learning, it remains common practice in deep learning to treat such problems as categorical classification using the categorical cross entropy loss.

Binary Classification regression

On Invariance Penalties for Risk Minimization

no code implementations17 Jun 2021 Kia Khezeli, Arno Blaas, Frank Soboczenski, Nicholas Chia, John Kalantari

We discuss the role of its eigenvalues in the relationship between the risk and the invariance penalty, and demonstrate that it is ill-conditioned for said counterexamples.

Domain Generalization

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