Ensembles of Exactly Solved Subsamples for Clusterwise Regression: Trimming Without a Trimming Level

The paper proposes an ensemble method for clusterwise regression that uses exact solutions on many small random subsamples. Each subsample is solved to global optimality, extended to the full data via nearest-surface assignment, and the resulting partitions are combined by voting or selection. The method achieves high accuracy even with up to 20% gross outliers and can estimate the trimming level without prior knowledge, outperforming traditional trimmed alternation in worst‑case scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.