Exploring Dimensionality Reduction Methods for Nonlinear Data: A Performance-Based Study

Dimensionality reduction plays a pivotal role in handling high-dimensional datasets by mitigating computational inefficiency, redundancy, and overfitting while preserving critical data structure. This paper evaluates three prominent dimensionality reduction techniques— Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Autoencoders—on a breast cancer dataset sourced from the SEER program. The study compares their performance across key metrics, including computational efficiency, reconstruction error, and structural preservation.