nevergrad

We have hosted the application nevergrad in order to run this application in our online workstations with Wine or directly.

Quick description about nevergrad:

Nevergrad is a Python library for derivative-free optimization, offering robust implementations of many algorithms suited for black-box functions (i.e. functions where gradients are unavailable or unreliable). It targets hyperparameter search, architecture search, control problems, and experimental tuning�domains in which gradient-based methods may fail or be inapplicable. The library provides an easy interface to define an optimization problem (parameter space, loss function, budget) and then experiment with multiple strategies�evolutionary algorithms, Bayesian optimization, bandit methods, genetic algorithms, etc. Nevergrad supports parallelization, budget scheduling, and multiple cost/resource constraints, allowing it to scale to nontrivial optimization problems. It includes visualization tools and diagnostic metrics to compare strategy performance, track parameter evolution, and detect stagnation.

Features:

• Multiple derivative-free optimization algorithms (evolution, Bayesian, bandits, genetic)
• Support for parallel execution and distributed evaluation of candidate solutions
• Budget and constraint management (e.g. total evaluations, cost limits)
• Visualization and diagnostic tools for optimization trajectories and performance
• Easy problem definition API (parameter spaces, loss functions, budgets)
• Strategy comparison framework to test and compare optimizers systematically

Programming Language: Python.
Categories: