English

Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning

Machine Learning 2026-05-12 v1

Abstract

Learned representations are often invariant to rotational transformations, leaving individual dimensions non-identifiable and interchangeable. We study how Matryoshka Representation Learning (MRL) induces a task-aligned privileged basis distinct from variance-based or regularizer-induced orderings. In the linear setting, we prove that full-prefix MRL recovers the ordered principal directions, and can be computed efficiently using shared statistics. Empirically, we demonstrate that MRL yields consistent per-dimension structure aligned with task signal, where coordinate magnitude reflects informativeness.

Keywords

Cite

@article{arxiv.2605.09160,
  title  = {Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning},
  author = {Arghamitra Talukder and Philippe Chlenski and Itsik Pe'er},
  journal= {arXiv preprint arXiv:2605.09160},
  year   = {2026}
}
R2 v1 2026-07-01T13:00:51.819Z