37 citations · 77 across the 22 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 3 cited
Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis
Alexander Munteanu, Simon Omlor, Zhao Song +1
A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independen…
cs.DS2022★ 3 cited
-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets
Alexander Munteanu, Simon Omlor, Christian Peters
We study the -generalized probit regression model, which is a generalized linear model for binary responses. It extends the standard probit model by replacing its link function,…