遗传算法Python 3.11实战5步实现函数优化与梯度下降对比当我们需要在复杂搜索空间中找到最优解时传统优化方法往往力不从心。遗传算法作为一种模拟自然进化过程的智能优化技术正成为解决这类问题的利器。本文将带您用Python 3.11从零实现遗传算法并对比其与梯度下降在函数优化中的表现差异。1. 遗传算法核心原理与Python实现遗传算法的魅力在于它将生物进化原理转化为数学优化工具。想象一群在解空间中探索的数字生物它们通过选择、交叉和变异不断进化最终逼近最优解。1.1 算法框架搭建我们先构建遗传算法的核心骨架import numpy as np from typing import List, Callable, Tuple class GeneticAlgorithm: def __init__(self, population_size: int, chromosome_length: int, fitness_func: Callable, crossover_rate: float 0.8, mutation_rate: float 0.01, elitism: bool True): self.pop_size population_size self.chrom_len chromosome_length self.fitness_func fitness_func self.crossover_rate crossover_rate self.mutation_rate mutation_rate self.elitism elitism def initialize_population(self) - np.ndarray: 生成随机初始种群 return np.random.uniform(-5.12, 5.12, (self.pop_size, self.chrom_len)) def selection(self, population: np.ndarray, fitness: np.ndarray) - np.ndarray: 轮盘赌选择 normalized_fitness fitness / fitness.sum() selected_indices np.random.choice( len(population), sizelen(population), pnormalized_fitness, replaceTrue) return population[selected_indices] def crossover(self, parent1: np.ndarray, parent2: np.ndarray) - Tuple[np.ndarray, np.ndarray]: 单点交叉 if np.random.rand() self.crossover_rate: return parent1.copy(), parent2.copy() crossover_point np.random.randint(1, self.chrom_len-1) child1 np.concatenate([parent1[:crossover_point], parent2[crossover_point:]]) child2 np.concatenate([parent2[:crossover_point], parent1[crossover_point:]]) return child1, child2 def mutation(self, individual: np.ndarray) - np.ndarray: 高斯变异 mask np.random.rand(self.chrom_len) self.mutation_rate noise np.random.normal(0, 0.5, self.chrom_len) return np.where(mask, individual noise, individual) def evolve(self, population: np.ndarray) - np.ndarray: 执行一代进化 fitness np.array([self.fitness_func(ind) for ind in population]) new_population np.empty_like(population) # 精英保留 if self.elitism: elite_idx np.argmax(fitness) new_population[0] population[elite_idx] start_idx 1 else: start_idx 0 # 选择 selected self.selection(population, fitness) # 交叉和变异 for i in range(start_idx, self.pop_size, 2): parent1, parent2 selected[i], selected[i1] child1, child2 self.crossover(parent1, parent2) new_population[i] self.mutation(child1) if i1 self.pop_size: new_population[i1] self.mutation(child2) return new_population1.2 适应度函数设计以Rastrigin函数为例这是一个典型的多模态优化问题def rastrigin(x: np.ndarray) - float: Rastrigin函数全局最小值在原点处为0 A 10 return A * len(x) np.sum(x**2 - A * np.cos(2 * np.pi * x)) def fitness_function(individual: np.ndarray) - float: 适应度函数将最小化问题转化为最大化问题 return -rastrigin(individual)Rastrigin函数在优化领域具有代表性其特点是具有大量局部极值点非常适合测试算法的全局搜索能力。2. 完整优化流程实现2.1 参数配置与算法执行def run_optimization(dimensions2, generations100, pop_size50, verboseTrue): 执行完整优化流程 ga GeneticAlgorithm( population_sizepop_size, chromosome_lengthdimensions, fitness_funcfitness_function, crossover_rate0.85, mutation_rate0.02 ) population ga.initialize_population() best_fitness_history [] avg_fitness_history [] for gen in range(generations): population ga.evolve(population) fitness_values np.array([fitness_function(ind) for ind in population]) best_fitness np.max(fitness_values) avg_fitness np.mean(fitness_values) best_fitness_history.append(best_fitness) avg_fitness_history.append(avg_fitness) if verbose and gen % 10 0: print(fGeneration {gen}: Best{-best_fitness:.4f}, fAvg{-avg_fitness:.4f}) best_idx np.argmax([fitness_function(ind) for ind in population]) best_solution population[best_idx] return best_solution, best_fitness_history, avg_fitness_history2.2 可视化收敛过程import matplotlib.pyplot as plt def plot_convergence(best_history, avg_history): 绘制适应度收敛曲线 plt.figure(figsize(10, 6)) plt.plot(-np.array(best_history), r-, labelBest Fitness) plt.plot(-np.array(avg_history), b--, labelAverage Fitness) plt.xlabel(Generation) plt.ylabel(Function Value) plt.title(Convergence History) plt.legend() plt.grid(True) plt.show() # 执行优化并可视化 best_solution, best_hist, avg_hist run_optimization(dimensions5) plot_convergence(best_hist, avg_hist) print(fOptimized solution: {best_solution}) print(fFinal value: {-best_hist[-1]:.6f})3. 梯度下降实现与对比3.1 梯度下降基础实现def gradient_descent(func: Callable, grad_func: Callable, initial_point: np.ndarray, learning_rate: float 0.01, max_iter: int 1000, tol: float 1e-6) - Tuple[np.ndarray, List[float]]: 标准梯度下降实现 x initial_point.copy() history [func(x)] for _ in range(max_iter): grad grad_func(x) x_new x - learning_rate * grad if np.linalg.norm(x_new - x) tol: break x x_new history.append(func(x)) return x, history def rastrigin_gradient(x: np.ndarray) - np.ndarray: Rastrigin函数的梯度 A 10 return 2 * x 2 * np.pi * A * np.sin(2 * np.pi * x)3.2 多起点梯度下降为公平比较我们实现多起点梯度下降def multi_start_gradient_descent(func: Callable, grad_func: Callable, dimensions: int, num_starts: int 20, max_iter: int 500) - Tuple[np.ndarray, float]: 多起点梯度下降 best_x None best_value float(inf) history [] for _ in range(num_starts): x0 np.random.uniform(-5.12, 5.12, dimensions) x, hist gradient_descent(func, grad_func, x0, learning_rate0.01, max_itermax_iter) history.extend(hist) current_value func(x) if current_value best_value: best_value current_value best_x x return best_x, best_value, history4. 性能对比分析4.1 定量对比实验我们设计实验对比两种算法的表现def run_comparison(dimensions2, trials10): 运行对比实验 ga_results [] gd_results [] for _ in range(trials): # 遗传算法 ga_solution, ga_history, _ run_optimization( dimensionsdimensions, verboseFalse) ga_results.append(rastrigin(ga_solution)) # 梯度下降 gd_solution, gd_value, _ multi_start_gradient_descent( rastrigin, rastrigin_gradient, dimensions) gd_results.append(gd_value) return ga_results, gd_results # 运行对比实验 ga_vals, gd_vals run_comparison(dimensions5, trials20) # 结果统计 print(Genetic Algorithm Results:) print(f Best: {np.min(ga_vals):.4f}) print(f Worst: {np.max(ga_vals):.4f}) print(f Average: {np.mean(ga_vals):.4f}) print(f Std Dev: {np.std(ga_vals):.4f}) print(\nGradient Descent Results:) print(f Best: {np.min(gd_vals):.4f}) print(f Worst: {np.max(gd_vals):.4f}) print(f Average: {np.mean(gd_vals):.4f}) print(f Std Dev: {np.std(gd_vals):.4f})4.2 结果可视化def plot_comparison(ga_values, gd_values): 绘制对比箱线图 plt.figure(figsize(10, 6)) plt.boxplot([ga_values, gd_values], labels[Genetic Algorithm, Gradient Descent]) plt.ylabel(Final Objective Value) plt.title(Performance Comparison (20 trials)) plt.grid(True) plt.show() plot_comparison(ga_vals, gd_vals)典型实验结果可能显示指标遗传算法梯度下降最优值0.00123.4521最差值0.856318.724平均值0.14259.8732标准差0.23144.56215. 高级技巧与参数调优5.1 关键参数影响分析遗传算法性能受多个参数影响种群大小太小多样性不足易早熟太大计算成本高推荐20-100复杂问题可更大交叉率典型值0.7-0.95高值促进信息交换低值减慢收敛变异率典型值0.001-0.05高值增加多样性但破坏优良解低值导致早熟收敛5.2 自适应参数调整实现自适应变异率def adaptive_mutation(self, individual: np.ndarray, generation: int, max_generations: int) - np.ndarray: 自适应变异率 base_rate self.mutation_rate # 随着代数增加逐渐降低变异率 adaptive_rate base_rate * (1 - generation/max_generations) mask np.random.rand(self.chrom_len) adaptive_rate noise np.random.normal(0, 0.5, self.chrom_len) return np.where(mask, individual noise, individual)5.3 混合策略结合两种算法优势def hybrid_optimization(dimensions, ga_generations50, gd_iterations100): 混合优化策略 # 先用GA进行全局搜索 ga GeneticAlgorithm(population_size50, chromosome_lengthdimensions, fitness_funcfitness_function) population ga.initialize_population() for _ in range(ga_generations): population ga.evolve(population) # 选择最佳个体进行梯度优化 best_idx np.argmax([fitness_function(ind) for ind in population]) best_solution population[best_idx] # 梯度下降局部优化 refined_solution, _ gradient_descent( rastrigin, rastrigin_gradient, best_solution, max_itergd_iterations) return refined_solution在实际项目中遗传算法特别适合以下场景目标函数不可导或不连续存在多个局部最优解参数空间非常大需要并行化处理而梯度下降在光滑凸问题上效率更高两者结合往往能取得最佳效果。
