Search Results for author: Ishana Shastri

Found 1 papers, 0 papers with code

Distribution of Classification Margins: Are All Data Equal?

no code implementations21 Jul 2021 Andrzej Banburski, Fernanda De La Torre, Nishka Pant, Ishana Shastri, Tomaso Poggio

Recent theoretical results show that gradient descent on deep neural networks under exponential loss functions locally maximizes classification margin, which is equivalent to minimizing the norm of the weight matrices under margin constraints.

Classification

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