Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Add a learned stochastic pair-interaction layer to a particle graph neural network, with a conditional normalizing flow generating the post-interaction relative state. Parameterize the update in center-of-mass and invariant relative coordinates so every sampled interaction preserves pair momentum and kinetic energy exactly. The flow learns the transition law directly from observed scattering or trajectory data, replacing repeated numerical collision solves or unconstrained message-passing…
Build a graph neural network on the dual graph of a triangulated surface whose messages are transported by \(\mathfrak{S}_3\) permutation matrices associated with adjacent-face color transports. This removes dependence on arbitrary local color-label choices and gives the network an explicit representation of noncontractible topology through holonomy around cycles.
Parameterize a nonnegative neural penalty or energy function as a sum of weighted power-mean differences applied to polynomial features of the network representation. Each atom is globally nonnegative by the power-mean inequality, so the learned penalty cannot become negative or destabilize constrained training, while the cone can represent polynomials outside SOS-plus-nonnegative-circuit certificates.
Split a recurrent state into two blocks and initialize their variances and cross-correlation according to the stationary projective energy distribution induced by the transition. This places the initial hidden state near the typical invariant direction of the dynamics instead of forcing a long transient from zero or isotropic noise.
Use the complex-conjugate palindromic coefficient that cancels the leading temporal phase defect of oscillatory modes. Implement complex arithmetic directly or use an exactly equivalent doubled-real state, then project the final state to its real component for real-valued prediction tasks.
Add a spectral regularizer to a learned graph or sparse attention adjacency that penalizes violation of the paper's energy floor. The regularizer discourages adjacency matrices that retain many edges but collapse into a low-dimensional spectral structure, which may reduce graph-message-passing diversity and worsen oversmoothing.
Use the graph Laplacian spectrum to set the mixing and correction coefficients of a two-state graph-propagation block. Balancing the contraction of low-frequency consensus modes against high-frequency disagreement modes may reduce oversmoothing and make deep graph-neural networks less sensitive to manually selected residual coefficients.
Add a fixed or weakly learned interface-localized branch to a sequence model. Set the critical mass term to zero and make the transport coefficient change sign across a learnable interface, producing a localized mode that pools information near a detected transition rather than averaging uniformly over the sequence.
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
Calibrate the scales of several additive self-adjoint residual or attention operators so their aggregate spectrum has a controlled higher-moment Berry–Esseen certificate. Penalize unusually large normalized (2+δ)-moments, which should reduce spectral outliers and make the summed operator closer to a predictable semicircle-shaped spectrum.
Add a two-output anti-collapse regularizer based on the determinant of the Jacobian Gram matrix, together with a penalty against proportional highest-degree coefficient tensors. The paper's inequality predicts that preserving coefficient non-proportionality prevents the output distribution from concentrating on thin curves or tiny regions, potentially improving coverage of a two-dimensional latent or generative output.
Augment spatial training examples by replacing a compact active region with several separated components while preserving its exact value histogram, total active area, and amplitude. The augmentation probes the nonlinear interaction between diffusion-like receptive fields and threshold activations, which the paper shows can make fragmented and compact inputs evolve in opposite directions despite identical distributions.
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.
Insert a fixed polynomial mixer before an MLP or retrieval index for tuples of discrete features. The mixer maps n+2 bounded scalar feature codes to one or several expanded scalar codes, and the paper's theorem guarantees that its image cannot collapse below order |A|^n when all coordinates come from a finite alphabet A. Use multiple independent permutations or coefficient choices to obtain a vector representation while retaining the deterministic algebraic structure.