47 citations · 112 across the 12 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
cs.LG2018★ 46 cited
Accelerating SGD with momentum for over-parameterized learning
Chaoyue Liu, Mikhail Belkin
Nesterov SGD is widely used for training modern neural networks and other machine learning models. Yet, its advantages over SGD have not been theoretically clarified. Indeed, as we…
cs.LG2018★ 3 cited
Parametrized Accelerated Methods Free of Condition Number
Chaoyue Liu, Mikhail Belkin
Analyses of accelerated (momentum-based) gradient descent usually assume bounded condition number to obtain exponential convergence rates. However, in many real problems, e.g., ker…