An accelerated minimal gradient method with momentum for strictly convex quadratic optimization
In this article we address the problem of minimizing a strictly convex quadratic function using
a novel iterative method. The new algorithm is based on the well-known Nesterov's …
a novel iterative method. The new algorithm is based on the well-known Nesterov's …
Provable Acceleration of Wide Neural Net Training via Polyak's Momentum
JK Wang, J Abernethy - openreview.net
Incorporating a so-called momentum dynamic in gradient descent methods is widely used in
neural net training as it has been broadly observed that, at least empirically, it often leads to …
neural net training as it has been broadly observed that, at least empirically, it often leads to …