Math: Logic

Machine-learning ideas tagged Logic in the Math taxonomy of the Math2NN corpus.

2 ideas found

△ Mechanism confirmed, baseline not beaten 2026

Biclique-free hierarchical attention

Replace dense token-to-token attention by a learned binary relation generated from a small number of hierarchical predicates, while rejecting masks that contain a fixed K_{t,t} biclique. The paper's incidence bound predicts near-linear active edges for these structured relations, giving sparse attention with a measurable worst-case complexity target rather than relying only on average sparsity.

Useful6/10

Difficulty6/10

Novelty6/10

Architecture Speedup Memory Scalability

Paper: Almost-linear Zarankiewicz bounds in $1$-semi-equational theories arXiv:2608.25464

Unverified 2026

Simultaneous-Label Sparse Attention

Replace a dense attention pattern by the exact intersection of a fixed or cheaply computed base graph H and a learned shared-label relation. Two tokens can exchange information only when they are adjacent in H and share at least one of d labels, producing a controllable structured sparsity pattern. The label count d becomes an explicit capacity and compute knob: increasing d enlarges the relation vocabulary without requiring a dense pairwise mask.

Useful5/10

Difficulty6/10

Novelty5/10

Architecture Memory Speedup Scalability

Paper: Simultaneous Graph Parameters and How to Bound Them arXiv:2608.06055