Metraipolis › archive › dc_bef81e95cb53
Certifiably Interpretable Training of ReLU-MLPs for Boolean Tasks with Guaranteed Truth-Table Generalization — arXiv:2609.13439
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13439
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:48:27.893Z
- SHA-256 of the archived text
52ba0692729367aaeeabc96117580032c037bd1bfab532f1789c31850d07b5e5- Stable URL of this page
https://metraipolis.com/documento/dc_bef81e95cb53
How to cite
Certifiably Interpretable Training of ReLU-MLPs for Boolean Tasks with Guaranteed Truth-Table Generalization — arXiv:2609.13439 — arXiv (en), https://arxiv.org/abs/2609.13439 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bef81e95cb53 (Metraipolis archive dc_bef81e95cb53, sha256 52ba0692729367aaeeabc96117580032c037bd1bfab532f1789c31850d07b5e5)
BibTeX
@misc{dcbef81e95cb53,
title = {Certifiably Interpretable Training of ReLU-MLPs for Boolean Tasks with Guaranteed Truth-Table Generalization — arXiv:2609.13439},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13439},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bef81e95cb53; sha256 52ba0692729367aaeeabc96117580032c037bd1bfab532f1789c31850d07b5e5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13439. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As compute scales, models evolve, and training algorithms advance, our ability to explain the increasingly powerful AI systems they enable is eroding. To help safeguard interpretability, we introduce a specialized training algorithm (MACCHIATO) that jointly constructs (i) an explicitly structured $\operatorname{ReLU}$-MLP from partial truth-table observations and (ii) an explicit Boolean circuit over signed literals with $\{\operatorname{AND},\operatorname{OR},\operatorname{XOR}\}$ gates certifying what its subnetworks compute and how they compose. Intuitively, we iteratively project the residuals of a Boolean function onto low-dimensional $\{\operatorname{AND},\operatorname{OR},\operatorname{XOR}\}$-circuit classes and exactly compile the resulting circuit into a $\operatorname{ReLU}$-MLP; we combine $\operatorname{ReLU}$-MLP circuit compilation, ESPRESSO logic minimization, and influence-based variable selection. Roughly speaking, our interpretability certificate is complemented by a statistical guarantee: under the theorem's influence-recovery conditions, if each of the $m$ stage-wise residuals depends on at most $\log_2(B)$ bits, a sample-splitting variant of our algorithm trained on $T$ observations returns a six-layer $\operatorname{ReLU}$-MLP (counting the input layer) of width $\mathcal{O}(mB)$ with truth-table error $\mathcal{O}\bigl(\sqrt{m(B+\log(m/\delta))/T}\bigr)$. On synthetic random-junta tasks, our networks outperform depth- and hidden-width-matched Adam-trained MLPs in several data-sparse or projection-aligned regimes, while the trained ReLU-MLPs are stronger in others. Moreover, in our explicit PyEDA truth-table implementation, the iterative procedure completes in regimes where flat ambient-dimensional ESPRESSO exceeds the three-hour computational budget.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.13439 — 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 2026-10-15T22:29:03.477Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).