Metraipolis › archive › dc_edf64c6422ee

Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization — arXiv:2610.01572

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01572
License (as archived)
CC0-1.0
Archived
2026-10-06T16:01:04.016Z
SHA-256 of the archived text
ba2e1bab82cc999123d9ff7bb2723449d3d0a89cf1758494a9d69ab9cf092972
Stable URL of this page
https://metraipolis.com/documento/dc_edf64c6422ee

How to cite

Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization — arXiv:2610.01572 — arXiv (en), https://arxiv.org/abs/2610.01572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edf64c6422ee (Metraipolis archive dc_edf64c6422ee, sha256 ba2e1bab82cc999123d9ff7bb2723449d3d0a89cf1758494a9d69ab9cf092972)
BibTeX
@misc{dcedf64c6422ee,
  title = {Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization — arXiv:2610.01572},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01572},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edf64c6422ee; sha256 ba2e1bab82cc999123d9ff7bb2723449d3d0a89cf1758494a9d69ab9cf092972},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper investigates stochastic multi-level optimization where the objective is a nested composition of several smooth non-convex functions. We assume that only stochastic estimates of the gradient and function values for each level are accessible. Consequently, obtaining an accurate estimate of the overall gradient is challenging due to the nested structure. To address this, we employ a momentum-based estimator with mini-batches to track the function values of each level, which are subsequently used to construct momentum gradient estimators. We establish an optimal sample complexity of $\mathcal{O}(\epsilon^{-4})$ for finding an $\epsilon$-stationary point, avoiding the stronger average smoothness assumption commonly relied upon in prior literature. Furthermore, by employing a normalization technique, we attain the same rate without requiring problem-dependent constants to set hyperparameters. To achieve the optimal rate without mini-batches, we further develop a batch-free method that incorporates a first-order approximation and a clipping technique for function value estimation. Finally, we validate the effectiveness of our proposed methods through experiments on risk-averse portfolio optimization and hierarchical tilted empirical risk minimization.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-02 in math.OC).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.01572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T15:14:57.974Z dalla pagina https://arxiv.org/catchup/math.OC/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).