Crate multistochgrad
source ·Modules§
- Some applications providing examples and tests. They show how implement Traits defined in types.rs to build a use case.
- Structure and functions to read MNIST database
- to include necessary files
- Implementation of basic Stochastic Average Gradient (SAG)
- A Rust implementation of Lei-Jordan papers:
- A Rust implementation of Johnson-Zhang paper:
“Acceleration stochastic Gradient Descent using Predictive Variance Reduction”
SVRG - This file is inspired by the crate optimisation written by Oliver Mader b52@reaktor42.de.
I kept the traits Function, FunctionC1, Summation and SummationC1 which provides the interface for users to define a minimisation problem.