digraph inheritance685c5dec64 { bgcolor=transparent; rankdir=TB; size=""; "SolverTuner" [URL="../lava-lib-optimization/lava.lib.optimization.utils.html#lava.lib.optimization.utils.solver_tuner.SolverTuner",fillcolor=white,fontname="Vera Sans, DejaVu Sans, Liberation Sans, Arial, Helvetica, sans",fontsize=10,height=0.25,shape=box,style="setlinewidth(0.5),filled",target="_top",tooltip="Utility class to optimize hyper-parameters by random search."]; }
class lava.lib.optimization.utils.solver_tuner.SolverTuner(search_space, params_names, shuffle=False, seed=0)

Bases: object

Utility class to optimize hyper-parameters by random search.

static generate_grid(params_domains)
property params_names: list
property results

Returns data on all hyper-parameters evaluations as a structured numpy array.

property search_space: list
property seed: int
property shuffle: bool
tune(solver, fitness_fn, fitness_target=None, config=SolverConfig(timeout=1000.0, target_cost=0, backend=<class 'lava.magma.core.resources.CPU'>, hyperparameters=None, probe_cost=False, probe_state=False, probe_time=False, probe_energy=False, log_level=40, folded_compilation=False))

Perform random search to optimize solver hyper-parameters based on a fitness function.

  • solver (OptimizationSolver) – Optimization solver to use for solving the problem.

  • fitness_fn (ty.Callable[[SolverReport], float]) – Fitness function to evaluate a given set of hyper-parameters, taking as input a SolverReport instance (refers to its documentation for the available parameters). This is the function that is maximized by the SolverTuner.

  • fitness_target (float, optional) – Fitness target to reach. If this is not passed, the full grid is explored before stopping search.

  • config (SolverConfig, optional) – Solver configuration to be used.


  • best_hyperparams (ty.Dict) – Dictionary containing the hyper-parameters with the highest fitness.

  • success (bool) – Flag signaling if the fitness_target has been reached. If no fitness_target is passed, the flag is True.