Acceleration via Fractal Learning Rate Schedules
Naman Agarwal 1 Surbhi Goel 2 Cyril Zhang 2
Abstract
In practical applications of iterative first-order
optimization, the learning rate schedule remains
notoriously difficult to understand and expensive step sizes γt1
Chebyshev nodes γt fractal schedule ηt
to tune. We demonstrate the presence of these
subtleties even in the innoc ...


雷达卡




京公网安备 11010802022788号







