Metraipolis › archive › dc_ab34ea70574a
Data Attribution via Sketched Metadifferentiation — arXiv:2609.15044
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15044
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:15:42.131Z
- SHA-256 of the archived text
a107749e42deb19cea3ce9f68c33a9628042151c98ab869c1bf1cad5b43ba6c0- Stable URL of this page
https://metraipolis.com/documento/dc_ab34ea70574a
How to cite
Data Attribution via Sketched Metadifferentiation — arXiv:2609.15044 — arXiv (en), https://arxiv.org/abs/2609.15044 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab34ea70574a (Metraipolis archive dc_ab34ea70574a, sha256 a107749e42deb19cea3ce9f68c33a9628042151c98ab869c1bf1cad5b43ba6c0)
BibTeX
@misc{dcab34ea70574a,
title = {Data Attribution via Sketched Metadifferentiation — arXiv:2609.15044},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15044},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab34ea70574a; sha256 a107749e42deb19cea3ce9f68c33a9628042151c98ab869c1bf1cad5b43ba6c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15044. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data attribution seeks to quantify how individual training examples shape a model's predictions and underpins problems including data valuation, machine unlearning, and model interpretability. Despite having a long line of work, computationally scalable methods often struggle to predict the effect of removing training data in neural networks due to their non-convex nature. To overcome this challenge, metagradient-based methods such as MAGIC (Ilyas and Engstrom, 2025) differentiate each prediction through the entire training run and compute its exact influence with respect to the training data, but require a separate run for every prediction. To reduce this cost, we cast budgeted attribution as estimating a large influence matrix from a small number of measurements. We show that the measurements most appropriate for recovering this matrix differ from those best suited for attribution itself. We then present two algorithms, MAGE and SPELL, suited for reconstruction and attribution respectively, that run on existing metagradient machinery at no extra cost. Empirical studies demonstrate strong performance over existing baselines across training scales and measurement budgets. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.15044 — 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 2026-10-15T23:54:14.939Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).