mlsanityData to 13 Oct 2026

Hierarchical Domain Generalization

arXiv 2607.16528 ↗First posted 17 Jul 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We study hierarchical domain generalization as a problem of extrapolation from finite observed regions to an entire instance space, replacing i.i.d. sampling with arbitrary domain hierarchies. We show that the central obstruction is not only the complexity of the hypothesis class, but the train/test domain partition through which evidence is revealed. In particular, no matter how small the class or how large the training size, some partition makes generalization fail for some target. These results suggest that modern generalization theory must treat domain structure as a first-class object.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 17 Jul 2026.

Builds on

13 of 20 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,106
  2. 2022Exploring Length Generalization in Large Language Modelscited by 205
  3. 2023What Algorithms can Transformers Learn? A Study in Length Generalizationcited by 198
  4. 2023Teaching Arithmetic to Small Transformerscited by 122
  5. 2023Generalization on the Unseen, Logic Reasoning and Degree Curriculumcited by 73
  6. 2024A Formal Framework for Understanding Length Generalization in Transformerscited by 44
  7. 2024Language Generation in the Limitcited by 40
  8. 2024Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformerscited by 39
  9. 2024Generation through the lens of learning theorycited by 31
  10. 2026Recursive Models for Long-Horizon Reasoningcited by 9
  11. 2025Quantitative Bounds for Length Generalization in Transformerscited by 8
  12. 2025Non-Asymptotic Length Generalizationcited by 7
1 more
  1. 2026Length Generalization Bounds for Transformerscited by 4

Built on by

Not cited yet.