Is margin preserved after random projection?
This addresses a theoretical gap in understanding margin preservation for random projections, which is incremental but relevant for machine learning algorithms using dimensionality reduction.
The paper analyzes margin distortion after random projection in binary and multiclass classification problems, providing conditions for margin preservation and theoretical bounds on multiclass margin in projected data.
Random projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this paper we analyse margin distortion after random projection, and give the conditions of margin preservation for binary classification problems. We also extend our analysis to margin for multiclass problems, and provide theoretical bounds on multiclass margin on the projected data.