Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent

09/05/2023
by   Stefano Di Giovacchino, et al.
0

Stochastic optimization methods have been hugely successful in making large-scale optimization problems feasible when computing the full gradient is computationally prohibitive. Using the theory of modified equations for numerical integrators, we propose a class of stochastic differential equations that approximate the dynamics of general stochastic optimization methods more closely than the original gradient flow. Analyzing a modified stochastic differential equation can reveal qualitative insights about the associated optimization method. Here, we study mean-square stability of the modified equation in the case of stochastic coordinate descent.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset