jaxopt
jaxopt copied to clipboard
Hardware accelerated, batchable and differentiable optimizers in JAX.
Is there a way to have multiple constraints with ProjectedGradient? For example can I have a constraint set be the intersection of the l2 sphere and non negative values?
`tol` is not parsed to `scipy.optimize.minimize` in `ScipyMinimize`.
Hi! I've been trying to use the scipy wrapper for the trust-ncg method. When I do this, I'm prompted to pass the hessian vector product as an argument. The source...
We have been working with @QB3 on a rework of #17, adding support functions to enable implicit differentiation with sparsity-inducing penalties. The main difference is that we are masking the...
Hello Everyone. First of all, thanks for this great library! I'm not sure if the following issue is with jaxopt or jax itself, but I started having problems applying vmap...
I am trying to run a complex nonlinear optimization on a multi-dimensional data using vmap on the solver.run. Since I could not use the l-bfgs-b method in the ScipyMinimize wrapper,...
Hi, all I found that the parameters of NN model are not updated when using gradient descent solver right before SGD. ```python import haiku as hk import jax import jax.numpy...