Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
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…
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.
Add a boundary-aware nonlocal regularizer to hidden-state sequences by subtracting the sharp Hardy weight from the fractional discrete-Laplacian energy. The resulting penalty is provably nonnegative on finite sequences under zero-padding at the left boundary, while its position-dependent Gamma-ratio weight concentrates protection near the sequence boundary.
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.
Add a norm-controlled feature mixer that applies a polynomial spectral filter to the channel covariance of a transformer or MLP block. A quadratic filter centered at \(\rho\) suppresses covariance eigenmodes far from the target and preserves modes near it, providing a tunable alternative to purely variance-maximizing mixing or standard normalization.
Construct metric-graph Laplacian positional encodings only at frequencies whose empirical eigenvalues are statistically stable under the paper’s $(n v_\mu(h))^{-1/2}$ law. Use local ball-mass estimates and empirical eigengaps to gate or downweight unreliable eigenvectors, preventing small-sample spectral noise from entering a GNN or graph transformer.
Represent intermediate feature maps on a periodic rectangular grid and regularize each individual Fourier eigenspace so that its spatial energy cannot collapse almost entirely outside a chosen observation region. The target lower bound is derived from the paper's quantitative rectangular estimate and is applied only to narrow Fourier shells, where the feature map is analogous to a degenerate Laplacian eigenfunction.
Replace dense token-to-token attention with a learned composition of adjacent routing operators whose connectivity is stored as a non-crossing labelled arc diagram. Canonicalize the composed routing program using the Okada relations, then execute only the surviving sparse token paths.
Replace an unconstrained linear residual adapter by an operator \(T\) satisfying a polynomial relation in the commutator operator \(\Delta_A(X)=AX-XA\). Choose the polynomial roots in a stable half-plane so that repeated commutators become nilpotent, making repeated adapter application terminate algebraically and permitting a finite-polynomial inverse of \(I+T\).
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.
Paper: $m$-Bell and $m$-Stirling numbers: Iterated binomial transforms, hyper-Bessel functions, and moments of the Conway--Maxwell--Poisson distributionarXiv:2608.12011
Replace explicitly stored independent random positional features with deterministic multiplicative phase features generated from a small table of random phases indexed by primes. Restrict positions to integers whose prime factors exceed a slowly growing threshold, because the paper's central-limit result says periodic weighted sums over these rough integers recover Gaussian behavior despite strong multiplicative dependence.
Add a structured boundary-like operation to an MoE router that rapidly mixes expert probabilities toward a learned distribution while preserving predefined expert groups. The operation is a rank-one stochastic kernel, so it costs linear rather than quadratic work in the number of experts and can act as a controlled reset when routing becomes concentrated.