[{"data":1,"prerenderedAt":12},["ShallowReactive",2],{"stack-tr-en-optuna":3},{"tagline":4,"description":5,"strengths":6,"useCase":11},"The hyperparameter-optimization framework that finds the right configuration in fewer trials.","Optuna defines the search space on the fly (define-by-run): each hyperparameter is sampled inside the objective function itself, which allows conditional and nested spaces. Its Bayesian TPE sampler proposes the next trials from previous results, its pruners (median, Hyperband) stop unpromising trials early, and studies run in parallel across machines through shared storage. Framework-agnostic, from boosting to PyTorch, it's our choice to replace grid search as soon as each training run costs more than a few minutes.",[7,8,9,10],"Define-by-run: conditional search spaces written in plain Python.","TPE, CMA-ES and Gaussian-process samplers, multi-objective optimization (NSGA-II).","Pruning of unpromising trials: median, successive halving, Hyperband.","Distributed studies on shared storage, visualization dashboard, common ML integrations.","Tuning boosters and neural networks, pipeline configuration, simulation optimization.",1792675979664]