# Understanding the Acceleration Phenomenon via High-Resolution Differential Equations

21 Oct 2018Bin ShiSimon S. DuMichael I. JordanWeijie J. Su

Gradient-based optimization algorithms can be studied from the perspective of limiting ordinary differential equations (ODEs). Motivated by the fact that existing ODEs do not distinguish between two fundamentally different algorithms---Nesterov's accelerated gradient method for strongly convex functions (NAG-SC) and Polyak's heavy-ball method---we study an alternative limiting process that yields high-resolution ODEs... (read more)

PDF Abstract