Metraipolis › archive › dc_0db01014576c

Learning Computational Structure for Sample-Efficient Prediction — arXiv:2610.28555

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.28555
License (as archived)
CC0-1.0
Archived
2026-10-21T07:08:35.557Z
SHA-256 of the archived text
cc2351d5ce1e7ad1036dc25a627e1b8356320e60bae3844662d5914285d8fbd9
Stable URL of this page
https://metraipolis.com/documento/dc_0db01014576c

How to cite

Learning Computational Structure for Sample-Efficient Prediction — arXiv:2610.28555 — arXiv (en), https://arxiv.org/abs/2610.28555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0db01014576c (Metraipolis archive dc_0db01014576c, sha256 cc2351d5ce1e7ad1036dc25a627e1b8356320e60bae3844662d5914285d8fbd9)
BibTeX
@misc{dc0db01014576c,
  title = {Learning Computational Structure for Sample-Efficient Prediction — arXiv:2610.28555},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.28555},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0db01014576c; sha256 cc2351d5ce1e7ad1036dc25a627e1b8356320e60bae3844662d5914285d8fbd9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Statistical learning in high dimensions suffers from the curse of dimensionality. Fortunately, many functions of practical interest are compositionally sparse, meaning they admit a composition of local functions, each depending on only a few variables, allowing sample complexity to depend on local arity rather than ambient dimension. Yet realizing this benefit requires exploiting hidden compositional structure, which theory does not establish for practical gradient-based training. We study this gap with CSFRBench, a controlled benchmark that hides the target's compositional computation during training but retains it for diagnosis, and find that dense networks and sparsity-based baselines leave much of that benefit unrealized. Inspired by the spatial organization of biological neural circuits, we introduce Learned Wiring (LeWi): each neuron has a learned low-dimensional embedding, only nearby neurons connect, and embeddings and weights are trained jointly. LeWi improves sample efficiency on targets with hierarchical structure, intermediate reuse, or independent modules. Across 32 additional targets generated by independently sampled computation graphs, LeWi is the most sample-efficient method not given the target graph, with 27% lower mean learning-curve area than dense networks. Dense networks perform better on targets with a single high-arity function. LeWi's representations and connectivity align with the target computation. On 17 world-model prediction tasks spanning control, navigation, and manipulation, LeWi beats the dense baseline on 16 and wins 99/119 baseline comparisons. These results show that jointly learning connectivity and weights can exploit computational structure to improve sample efficiency.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.28555 — 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 2026-10-21T07:05:43.666Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).