no code implementations • 11 Aug 2023 • Jiajun Luo, Trambak Banerjee, Gourab Mukherjee, Wenguang Sun
As the dimension of the auxiliary data increases, we accurately quantify the improvements in estimation risk and the associated deterioration in convergence rate.
no code implementations • 26 Apr 2023 • Trambak Banerjee, Bhaswar B. Bhattacharya, Gourab Mukherjee
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.
no code implementations • NeurIPS 2021 • Atal Narayan Sahu, Aritra Dutta, Ahmed M. Abdelmoniem, Trambak Banerjee, Marco Canini, Panos Kalnis
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.