Enayat Ullah

activity

20182026

most citedConvergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration

82 citations · 181 across the 16 of their papers we have counts for

collaborators

Showing 2018Show all

2 papers · 1 filter

cs.LG2018★ 1 cited

Streaming Kernel PCA with $O ~ (n)$ Random Features

Enayat Ullah, Poorya Mianjy, Teodor V. Marinov +1

We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, $O (n lo g n)$ f…

cs.LG2018★ 82 cited

Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration

Soham De, Anirbit Mukherjee, Enayat Ullah

RMSProp and ADAM continue to be extremely popular algorithms for training neural nets but their theoretical convergence properties have remained unclear. Further, recent work has s…

Streaming Kernel PCA with O~(n​) Random Features

Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration

Streaming Kernel PCA with $O ~ (n)$ Random Features