Jaxopt

New features

- Added MAML example by Fabian Pedregosa based on initial code by Paul Vicol and Eric Jiang.
- Added the possibility to stop LBFGS after a line search failure, by Zaccharie Ramzi.
- Added gamma to LBFGS state, by Zaccharie Ramzi.
- Added jaxopt.BFGS, by Mathieu Blondel.
- Added value_and_grad option to all gradient-based solvers, by Mathieu Blondel.
- Added Fenchel-Young loss, by Quentin Berthet.
- Added projection_sparse_simplex, by Tianlin Liu.

Bug fixes and enhancements

- Fixed missing args,kwargs in resnet example, by Louis Béthune.
- Corrected the implicit diff examples, by Zaccharie Ramzi.
- Small optimization in l2-regularized semi-dual OT, by Mathieu Blondel.
- Numerical stability improvements in jaxopt.LevenbergMarquardt, by Amir Saadat.
- Dtype consistency in LBFGS, by Alex Botev.

Deprecations

- jaxopt.QuadraticProgramming is now fully removed. Use jaxopt.CvxpyQP, jaxopt.OSQP, jaxopt.BoxOSQP and jaxopt.EqualityConstrainedQP instead.

Contributors

Alex Botev, Amir Saadat, Fabian Pedregosa, Louis Béthune, Mathieu Blondel, Quentin Berthet, Tianlin Liu, Zaccharie Ramzi.

New features

- Added optimal transport related projections: projection_transport, projection_birkhoff, kl_projection_transport, and kl_projection_birkhoff, by Mathieu Blondel (semi-dual formulation) and Tianlin Liu (dual formulation).

Bug fixes and enhancements

- Fix LaTeX rendering issue in notebooks, by Amélie Héliou.
- Avoid gradient recompilations in zoom line search, by Mathieu Blondel.
- Fix unused Jacobian issue in jaxopt.ScipyRootFinding, by Louis Béthune.
- Use zoom line search by default in jaxopt.LBFGS and jaxopt.NonlinearCG, by Mathieu Blondel.
- Pass tolerance argument to jaxopt.ScipyMinimize, by pipme.
- Handle has_aux in jaxopt.LevenbergMarquardt, by Keunhong Park.
- Add maxiter keyword argument in jaxopt.ScipyMinimize, by Fabian Pedregosa.

Contributors

Louis Béthune, Mathieu Blondel, Amélie Héliou, Keunhong Park, Fabian Pedregosa, pipme.

New features

- Added zoom line search in jaxopt.LBFGS, by Mathieu Blondel. It can be enabled with the linesearch="zoom" option.

Bug fixes and enhancements

- Added support for quadratic polynomial fun in jaxopt.BoxOSQP and jaxopt.OSQP, by Louis Béthune.
- Added a notebook for the dataset distillation example, by Amélie Héliou.
- Fixed wrong links and deprecation warnings in notebooks, by Fabian Pedregosa.
- Changed losses to avoid roundoff, by Jack Valmadre.
- Fixed init_params bug in multiclass_svm example, by Louis Béthune.

Contributors

Louis Béthune, Mathieu Blondel, Amélie Héliou, Fabian Pedregosa, Jack Valmadre.

Bug fixes and enhancements

- Fix issue with positional arguments in jaxopt.LBFGS and jaxopt.NonlinearCG, by Mathieu Blondel.

Bug fixes and enhancements

- Improvements in [jaxopt.LBFGS](https://github.com/google/jaxopt/releases/_autosummary/jaxopt.LBFGS.html#jaxopt.LBFGS): fixed bug when using use_gamma=True, added stepsize option, strengthened tests, by Mathieu Blondel.
- Fixed link in resnet notebook, by Fabian Pedregosa.

Contributors

Fabian Pedregosa, Mathieu Blondel.

New features

- Added solver jaxopt.LevenbergMarquardt, by Amir Saadat.
- Added solver jaxopt.BoxCDQP, by Mathieu Blondel.
- Added projection_hypercube, by Mathieu Blondel.

Bug fixes and enhancements

- Fixed solve_normal_cg when the linear operator is “nonsquare” (does not map to a space of same dimension), by Mathieu Blondel.
- Fixed edge case in jaxopt.Bisection, by Mathieu Blondel.
- Replaced deprecated tree_multimap with tree_map, by Fan Yang.
- Added support for leaf cond pytrees in tree_where, by Felipe Llinares.
- Added Python 3.10 support officially, by Jeppe Klitgaard.
- In scipy wrappers, converted pytree leaves to jax arrays to determine their shape/dtype, by Roy Frostig.
- Converted the “Resnet” and “Adversarial Training” examples to notebooks, by Fabian Pedregosa.

Contributors

Amir Saadat, Fabian Pedregosa, Fan Yang, Felipe Llinares, Jeppe Klitgaard, Mathieu Blondel, Roy Frostig.