Sparse principal component analysis via axis-aligned random projections
This provides a more reliable approach to sparse PCA for statisticians and data scientists by avoiding initialization issues common in iterative methods.
The authors tackled sparse principal component analysis by introducing a non-iterative method based on aggregating eigenvectors from axis-aligned random projections, achieving minimax optimal convergence rates with polynomial-time computation and demonstrating competitive finite-sample performance.
We introduce a new method for sparse principal component analysis, based on the aggregation of eigenvector information from carefully-selected axis-aligned random projections of the sample covariance matrix. Unlike most alternative approaches, our algorithm is non-iterative, so is not vulnerable to a bad choice of initialisation. We provide theoretical guarantees under which our principal subspace estimator can attain the minimax optimal rate of convergence in polynomial time. In addition, our theory provides a more refined understanding of the statistical and computational trade-off in the problem of sparse principal component estimation, revealing a subtle interplay between the effective sample size and the number of random projections that are required to achieve the minimax optimal rate. Numerical studies provide further insight into the procedure and confirm its highly competitive finite-sample performance.