Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Represent selected activations, weights, or optimizer accumulators as four floating-point limbs and evaluate products through tensor-core matrix multiplications encoding limb convolution. Retain the convolution components during reductions and renormalize only at block boundaries, avoiding branch-heavy multi-double arithmetic inside every multiply-add.
Augment a graph neural network or graph transformer with counts of cyclic walks whose successive steps are required to be graph edges or graph non-edges according to a binary pattern. These features encode induced-subgraph structure that ordinary adjacency powers miss, and can be concatenated to the graph-level token or used as an auxiliary prediction target.
Replace an ordinary token aggregation step with a p-replica cyclic-equivariant block. Features are copied into p replicas, processed by shared operators, coupled through a cap-like bilinear interaction, and projected onto cyclic invariants. An auxiliary commutation loss enforces that applying the operator before or after the p-fold lift gives similar outputs.
Replace an unconstrained order-k weight tensor with a sum of components that are symmetric only within selected contiguous index blocks. This preserves interactions between blocks while tying parameters under within-block permutations, providing a tunable middle ground between a fully dense tensor and a fully symmetric tensor.
Use the logarithmic exhaustion as a geometry for bounded hidden representations rather than only as a parameter constraint. A representation approaching the boundary receives an increasingly large metric, making ordinary Euclidean motion expensive and discouraging brittle saturation while preserving a bounded intrinsic gradient for the boundary coordinate.
Treat each directed attention matrix as a graph transition matrix and form its Laplacian L = I - A. Compute the principal-cofactor vector to identify tokens with weak global access to the rest of the layer, and regularize the nonzero-eigenvalue product so attention does not become reducible or nearly singular. This targets pathological attention heads that isolate token groups and produce unstable or poorly propagated representations.
Replace ordinary dot-product attention logits with a strictly totally positive kernel evaluated on positive, ordered scalar coordinates attached to queries and keys. Use the modified-Bessel kernel K(x,s)=I_s(x), whose every ordered minor is positive, then row-normalize it as an attention matrix. This creates an attention operator with a mathematically enforced anti-oscillatory structure rather than merely positive entries.
Add a Vandermonde conditioning objective to a mixture-of-experts router so that experts acquire distinct scalar routing signatures instead of collapsing onto the same score region. The regularizer uses powers of one learned scalar score and directly penalizes near-coincident expert scores, providing a finite-mode identifiability signal complementary to load balancing.
Paper: Reduced characteristic number criteria for equivariant bordism of $T^k$- and $(\mathbb{Z}_2)^k$-manifolds with isolated fixed pointsarXiv:2607.01889
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.
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 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
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.