Solves: Scalability

Machine-learning ideas tagged Scalability in the Solves taxonomy of the Math2NN corpus.

Unverified 2026

Matroid-circuit equivariant message passing

Represent each matroid circuit as a structured hyperedge and perform message passing from circuit embeddings back to their constituent elements. Tie all circuit-update parameters that lie in the same automorphism orbit, so relabelings preserving the matroid produce exactly relabeled hidden states rather than requiring the network to learn this symmetry from data.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Encoding matroids into quantum states arXiv:2607.02736
Unverified 2026

Tree-Cone Distribution Head

Represent a neural network's categorical output over a rooted tree using cumulative probability mass on each rooted subtree. Train pairs of examples with a stochastic-dominance loss that compares these subtree masses, avoiding enumeration of all upper sets and making hierarchical monotonicity explicit. This is suitable for taxonomies, severity levels, hierarchical intents, and structured world-model states.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: Characterizing finite posets whose probabilistic powerdomain are RB-domains arXiv:2607.02231
Unverified 2026

Sharp Sumset Support Regularizer

Apply the paper's sharp sumset lower bound to the active discrete supports of multiple additive branches in a sparse neural layer. Penalize cases where the support of the combined output is smaller than the mathematically guaranteed minimum implied by the branch supports, discouraging destructive overlap and representational collapse.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Sharp Lower Bounds for Sumsets in Hypercubes arXiv:2607.01458
Unverified 2026

Rank-safe Bernoulli layer initialization

Use the Bernoulli corank asymptotic to choose sparsity for binary or sparse linear layers and reject initial matrices with excessive numerical rank deficiency. The layer should also explicitly prevent zero columns, because the paper's probability law indicates that zero-column events are a leading mechanism behind large corank in the sparse regime.

Useful5/10
Difficulty4/10
Novelty5/10
Paper: Rank deficiency of Bernoulli random matrices for growing corank arXiv:2607.00495
Unverified 2026

Poisson–Kingman expert-capacity prior

Replace the usual uniform expert-load target in sparse MoE training with a random, heavy-tailed capacity allocation generated by a conditioned Poisson point process. The constant profile reproduces a Poisson–Dirichlet-like allocation, while a profile such as \(\phi_\gamma(x)=1+e^{-\beta\gamma x}\) deliberately changes the frequency of large versus small expert allocations.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Macroscopic Feynman Cycles and Poisson--Kingman Universality in Bose Condensation arXiv:2607.04264
Unverified 2026

Simplex-Complexity Depth Diagnostic

Estimate the simplex-based ratio of a target or learned convex piecewise-linear polytope and use the theorem \(\rho_\Delta(P)\le 2^d-1\) to choose a minimum useful ReLU depth. During training, monitor whether the learned polytope is approaching a high-\(\rho\) target; if it is, widen the model without increasing depth only when the diagnostic indicates that depth is the bottleneck.

Useful5/10
Difficulty5/10
Novelty9/10
Paper: A simplex-based measure of symmetry arXiv:2607.03815
Unverified 2026

Leading-Term Strand Router

Build a sparse neural mixing layer from colored directed strands rather than a dense all-to-all matrix. Feature channels are assigned ordered colors, local trivalent junctions conserve every color, and an edge width is the weighted sum of the colors carried by that edge; a differentiable penalty favors monotone, crossing-free routings that define a canonical leading term. This creates a structured routing prior that can be compared directly against dense attention and unconstrained sparse…

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Leading term strandings for webs arXiv:2608.27425
Unverified 2026

Boxicity-guided constraint attention

Replace an unconstrained pairwise attention score with an intersection of coordinate-wise threshold or interval compatibility heads. Each head is a supergraph that permits pairs satisfying one constraint, while the final attention edge exists only when every head permits the pair. This provides an interpretable inductive bias for multi-constraint relations and prevents the model from approximating a conjunction using a single unstable nonlinear score.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Boxicity and Threshold Dimension of Zero Divisor Graphs arXiv:2608.27381
Unverified 2026

Compositional Contraction Budget for Residual Blocks

Estimate how strongly each neural block contracts distinguishability and use the paper's weighted composition inequality to allocate depth, residual strength, or precision where information is actually preserved. Blocks that strongly contract information beyond the reference path receive a smaller residual gate, higher numerical precision, or are replaced by a cheaper identity-like operation.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Conditional contraction coefficients and their applications to quantum networks arXiv:2608.27171
Unverified 2026

Quasiperiodic Additive State Module

Use the paper's skew product as a parameter-free recurrent state: one phase rotates by an irrational increment and a second state accumulates a lacunary Fourier readout of that phase. This supplies deterministic long-range memory with only scalar updates, avoiding a learned recurrent transition matrix and its potentially unstable spectrum.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Regularity, quantitative deviation, and non-rigidity of a lacunary skew product arXiv:2608.25821
Unverified 2026

Collision-free ternary attention

Represent a sparse higher-order attention head by a 3-uniform hypergraph whose hyperedge $(v,x,y)$ allows anchor token $v$ to aggregate a pairwise interaction between tokens $x$ and $y$. During mask construction, greedily reject edges that would create a $4$-cycle in the link graph $L(v)$, so the same pair of source tokens cannot reach an anchor through multiple redundant pairings. This produces a diversity-constrained sparse attention pattern with an explicit, measurable collision bound.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Regularity method for hypergraphs with $4$-cycle-free links arXiv:2608.24740
Unverified 2026

Möbius-compressed circular latent states

Represent a population of N circular latent states using a three-parameter Möbius transformation applied to fixed uniform reference phases, rather than learning N unrelated angles. The resulting states remain on the circle by construction and can model concentrated or nearly uniform phase populations through a single concentration parameter.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Unstable Manifolds for the Kuramoto Model: Convergence to the Ott-Antonsen Manifold arXiv:2608.24453
Unverified 2026

Branching-Pressure Router

Replace a generic MoE router entropy bonus with a branching-pressure objective that values routes according to both their stochastic entropy and their number of valid fine-grained continuations. The module can be implemented as a hierarchical router: a coarse state chooses a base transition, while a validity mask determines how many valid expert or latent branches lift that transition.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: The entropy of Gromov-Thurston manifolds and branched coverings arXiv:2608.24220
Unverified 2026

Rotor-Router Neighborhood Sampler

Replace independently sampled random-walk paths used for GNN neighbor or subgraph sampling by persistent rotor walks on the training graph. Each node stores a pointer into a fixed cyclic ordering of its outgoing neighbors; every visit advances the pointer and selects the next neighbor, producing deterministic coverage with no repeated random choices. Use several short rotor trajectories per seed and periodically reinitialize only the rotors in an encountered subgraph.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Eulerian walkers on $\mathbb{Z}^2$ have range exponent $2/3$ arXiv:2608.23545
Unverified 2026

Curvature-certified cycle suppression

Add a curvature-aware structural regularizer to a graph neural network or learned graph-rewiring module. The regularizer raises low-curvature edges toward the sharp 1/2 threshold, which is predicted to suppress first-dimensional cycle-space structure and reduce redundant or conflicting message-passing routes without explicitly computing graph homology.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: A Sharp Curvature Threshold for GLMY Path Homology arXiv:2608.23187
Unverified 2026

Fisher-Geometry Expert Menu

Construct a finite menu of experts or LoRA adapters by quantizing the oracle action manifold under a task-aware Fisher-information distortion rather than Euclidean parameter distance. The router can choose an installed expert after observing the input, but only k experts are stored or evaluated. The paper's frontier rate gives a falsifiable accuracy-versus-menu-size prediction.

Useful5/10
Difficulty6/10
Novelty4/10
Paper: Pre-Disclosure Experiment Menus: Oracle-Relative Risk and Joint Sample--Menu Asymptotics arXiv:2608.22905
Unverified 2026

m-Binomial Global Mixer

Insert a fixed or lightly gated lower-triangular binomial-transform layer into a sequence model to create global interactions across positions without forming attention logits. For a sequence of length N, mix each output position with all earlier positions using coefficients determined by an integer m; initialize the layer fixed and optionally learn a diagonal channel gate or a small mixture over m values.

Useful4/10
Difficulty5/10
Novelty8/10
Paper: $m$-Bell and $m$-Stirling numbers: Iterated binomial transforms, hyper-Bessel functions, and moments of the Conway--Maxwell--Poisson distribution arXiv:2608.12011
Unverified 2026

Multiplicity-free Schur channel tying

Tie neural parameters across feature channels according to the Schur multiplicity pattern of the fermionic coinvariant representation. In the two-fermion case, use one learned parameter block for each Schur degree instead of independently parameterizing every ordered pair of fermionic channels, eliminating redundant copies while preserving the relevant GL2 channel symmetry.

Useful4/10
Difficulty5/10
Novelty7/10
Paper: Type $B$ fermionic coinvariant rings arXiv:2608.02881
Unverified 2026

Higher-Order Coactivation Envelope

Convert an attention or MoE routing affinity matrix into a soft graph and constrain its K_r-density relative to its observed K_s-density. The regularizer penalizes pathological affinity patterns in which moderate s-way coactivation is accompanied by an implausibly low or unstable r-way coactivation.

Useful4/10
Difficulty5/10
Novelty7/10
Paper: A Higher-Order Clique Density Theorem arXiv:2607.06545
Unverified 2026

Reaction-Closed Sparse Routing

Represent the active experts or channels of a sparse layer by a presence set and impose a reaction-style dependency graph on possible support changes. During a growth phase, activate only the least support set closed under enabled dependencies; during later pruning, allow trajectory-dependent removals but never add structurally unreachable experts. This should reduce routing churn and dead experts while preserving adaptive sparsity.

Useful4/10
Difficulty5/10
Novelty7/10
Paper: A Structural Theory of Admissible Transitions in Biological Reaction Networks arXiv:2608.27201