particle-swarm

What problem does it solve?

Particle Swarm Optimization (PSO) solves continuous, high-dimensional optimization problems by simulating a swarm of candidate solutions that collaboratively search for optima in the search space.

Core Features & Use Cases

• Parameter tuning for machine learning, control, and engineering tasks.
• Fast convergence on smooth objectives with a small set of tunable parameters.
• Educational demonstrations and rapid prototyping of optimization workflows.
• Use Case: Calibrating parameters for a model; optimizing a multi-dimensional objective function within bounds.

Quick Start

1. Define objective function and bounds for each decision variable.
2. Instantiate the PSO engine, e.g. ParticleSwarmOptimization(objective, bounds, n_particles=30).
3. Call optimize() to obtain the best solution and convergence history.