Stochastic (L-)BFGS

Anyone knows of a julia implementation of a stochastic (L-)BFGS variant, like e.g. described here or described here or implemented in pytorch here?

1 Like

GitHub - baggepinnen/FluxOptTools.jl: Use Optim to train Flux models and visualize loss landscapes has an implementation, but I haven’t tested it much.

1 Like