search

abess-team / skscope

skscope: Sparse-Constrained OPtimization via itErative-solvers
https://skscope.readthedocs.io
MIT License
302 stars 13 forks source link

[Feature] Support for sparse matrix and more optimizers #79

Open chenpnn opened 3 months ago

chenpnn commented 3 months ago

I have two suggestions for possible improvements as follows:

  1. Sparse matrix: In some practical problems (e.g., document classification) where the covariate matrix is extremely sparse, can skscope utilize the characteristic of sparse matrix to imporve the efficiency of storage and computation? Some reference may be helpful such as scipy.sparse or its JAX version jax.scipy.sparse.
  2. Optimizers: I find that the base numeric solver for skscope is mainly based on nlopt now, and I wonder whether it is possible to support more optimizers. For example, the differentiable optimizer JAXopt may be more suitable for general (unconstrained, constrained and composite) optimization problems .

Thanks!

Mamba413 commented 3 months ago

The requested feature also covers this one: https://github.com/abess-team/skscope/issues/58