Skip to main content

> ML_ALGORITHM // NON-DOMINATED-SORTING-GENETIC-ALGORITHM-NSGA-II_v1.0

NSGA-II (Non-dominated Sorting Genetic Algorithm II)

The industry-standard multi-objective evolutionary algorithm that finds a diverse set of Pareto-optimal tradeoff solutions using fast non-dominated sorting.

Multi-Objective Optimizationevolutionary-searchhigh-intrinsicsmall (<1k)
Back to All Algorithms
Computational Complexity
Training Complexity:O(generations * M * population_size^2) where M is number of objectives
Inference Complexity:O(1)
Hardware Profile
CPU Friendly:Yes
Requires GPU:No
Memory Footprint:low
Interpretability & Data
Interpretability Tier:high-intrinsic
Training Data Needs:small (<1k)

Interpretability Assessment

Directly yields the full Pareto frontier of optimal tradeoff solutions for stakeholder selection.

Suitable Tasks & Supported Modalities

Suitable Tasks:
multi objective optimizationmodel compression nastradeoff analysis
Supported Modalities:
tabular

Implementing Libraries

pymoo
deap

Foundational Literature

Common Pitfalls & Warnings
  • When objectives exceed 3 or 4 (many-objective optimization), almost all solutions become non-dominated, causing selection pressure to collapse (use NSGA-III instead)