Search Results for author:
Found 3 papers, 0 papers with code
Empirical Bayes Estimation with Side Information: A Nonparametric Integrative Tweedie Approach
As the dimension of the auxiliary data increases, we accurately quantify the improvements in estimation risk and the associated deterioration in convergence rate.
Bootstrapped Edge Count Tests for Nonparametric Two-Sample Inference Under Heterogeneity
In this regime, we study the asymptotic behavior of weighted edge count test statistic and show that it can be effectively re-calibrated to detect arbitrary deviations from the composite null.
Rethinking gradient sparsification as total error minimization
Unlike with Top-$k$ sparsifier, we show that hard-threshold has the same asymptotic convergence and linear speedup property as SGD in the convex case and has no impact on the data-heterogeneity in the non-convex case.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
