1 مستودع
Toolkits providing algorithms for function optimization that do not require gradient information.
Distinct from Gradient Descent Algorithms: Contrasts with gradient-descent algorithms by specifically avoiding the use of derivatives.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Gradient-Free Optimization Libraries. Refine with filters or upvote what's useful.
Nevergrad is a gradient-free optimization library and hyperparameter optimization framework designed to find the minimum of objective functions without using derivatives. It serves as an asynchronous optimization engine that decouples parameter suggestions from result reporting to support parallel function evaluations. The project specializes in multi-objective optimization to identify Pareto fronts for competing goals and provides a suite for benchmarking the performance and convergence of different optimization routines. It supports black-box system optimization, enabling the tuning of exte
Functions as a comprehensive toolkit for finding function minima using adaptive algorithms without derivatives.