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 centered triangle-consistency term to a graph neural network or graph transformer. The term rewards learned edge affinities whose triangle products exceed the independent-edge baseline while preserving the overall edge density, encouraging locally coherent neighborhoods instead of arbitrary pairwise affinities.
Normalize attention or router logits and control their upper tail using the paper's sharper Gaussian-maximum exponent rather than a correlation-blind sub-Gaussian bound. Use the resulting threshold to add a soft penalty or adaptive temperature whenever the observed maximum exceeds the calibrated level, reducing rare one-token or one-expert domination.
Replace a singular inverse interaction kernel by the finite part of its meromorphic continuation at an exceptional dimension, producing an explicit polynomial-times-logarithm feature interaction. This gives a controlled alternative to adding an arbitrary ridge term when a learned polynomial Gram matrix becomes rank-deficient.
Replace one dense attention layer with a sparse hierarchical attention module whose states are clusters of tokens and whose transitions merge two clusters or reverse a previous merge. Enforce the flag-space cancellation law on pairs of alternative two-step merge paths, so redundant hierarchical routes destructively interfere instead of producing duplicated features. Normalize merge-then-unmerge loops using the product of the sizes of the merged clusters, preventing large clusters from…
Use local split-fusion rewrites as a structured alternative to globally recomputing token clusters. A model proposes a small number of neighboring tree edits per input, accepts only valid edits that reduce a learned energy, and retains the previous hierarchy across layers or decoding steps.
Replace one-step greedy landmark selection in Nyström attention or kernel compression with a restricted pairwise-lookahead rule. The lookahead is motivated by the paper's explicit obstruction: a signed triangle can make individual column gains exhibit increasing rather than diminishing returns, so the best next column need not belong to the best pair.
Add a clique-aware penalty to a learned graph adjacency or graph-attention matrix that suppresses excessive squared positive eigenvalue energy. Unlike a spectral-radius penalty, this controls the entire positive spectral subspace and can discourage highly concentrated, unstable message-passing channels while preserving useful negative-spectrum structure.
Augment a representation-learning objective with penalties enforcing the paper's four-point metric inequalities, and use an exponential snowflake kernel instead of unconstrained dot-product similarity. The experiment tests whether geometrically valid similarities improve retrieval or attention stability at equal model size and compute.
Use the isolated positive spectral mode created by a finite branch defect on an otherwise long cycle as a graph positional feature. The feature should concentrate around structurally unusual vertices while remaining insensitive to the total cycle length, providing a principled alternative to raw Laplacian eigenvectors for cycle-with-branch graphs.
Replace a locally oriented three-channel feature frame by its positive-definite polar factor, removing arbitrary SO(3) basis rotations before the feature enters an MLP, attention block, or graph message-passing layer. Process the resulting SPD matrix in log coordinates so the downstream network receives a globally unconstrained symmetric representation rather than a gauge-dependent frame.
Learn or select sparse cyclic convolution or relative-attention offsets whose pairwise differences collide less often modulo the sequence length. The paper's Fourier fourth-power identity turns this combinatorial objective into an FFT-computable differentiable loss, enabling fixed-K sparse patterns with lower aliasing and interference than random offsets.
Build a graph diffusion or neural-operator encoder whose sparse-observation loss is weighted according to graph distance from the observed nodes. For early diffusion times, suppress supervision or cross-attention demands that are geometrically impossible because signals at distance \(d\) are attenuated like \(e^{-d^2/(2t)}\); gradually release those constraints as diffusion time grows.
Replace an unconstrained bilinear matrix fusion or covariance head with \(\Phi(A,B)=\sum_{r=1}^R V_r^*(A\otimes B)V_r\). The output is PSD by construction, and the stronger block-level property makes the layer compatible with minibatches, mixtures, and Gram-matrix inputs rather than merely preserving positivity pointwise.
Use eigenvector delocalization as a mask-quality criterion rather than selecting a random sparse graph blindly. Penalize masks whose normalized adjacency has concentrated leading eigenvectors or disconnected or weakly connected components, while preserving the power-law distance prior. This creates a sparse routing graph that is less likely to trap information in local regions.
Replace or augment relative-position attention with a positive fractional-integration mixing kernel whose radial behavior has separate inner and outer power laws. Tokens close to one another interact through the usual fractional singularity, while tokens near different radial scales receive a ground-state correction that can improve multiscale information transport without introducing a dense learned positional table.
Represent tokens, features, or attention states by normalized rank-one matrices and train the network to preserve their Schatten-p distance profiles over complex phase rotations. Because the paper proves that equality of all distances \(\|\lambda e-v\|_p\) identifies \({\rm Tr}(e^*v)\), this regularizer preserves matrix overlap geometry under a learned transformation.
Constrain a learned binary graph or sparse attention-routing graph so that every node neighborhood has no independent set of size k. This local anti-star condition gives an explicit upper bound on the graph Laplacian spectral radius, allowing a larger but certified stable diffusion step or residual propagation coefficient.
Build a neural architecture whose receptive field or attention span is increased according to an estimated disorder-to-order crossover scale. Local branches process windows below the crossover as if they were stochastic, while a global branch is activated only when the context exceeds the predicted scale needed to expose deterministic recurrence. This targets sequences or images containing long-range quasiperiodic, hierarchical, or algorithmically generated structure that is statistically…
Represent each feature as belonging to one of three \(\mathbb{Z}_3\) charge sectors and constrain every linear and multiplicative operation to obey charge addition modulo 3. Add invariant cubic gates such as \(x_1x_2x_3\) or \(x_q^3\), which can express the same phase-insensitive interaction selected by the paper's three-photon drive. This should improve data efficiency and exact cyclic-augmentation consistency when the task has a genuine ternary symmetry.
Replace or augment conventional dot-product attention with features generated by a convex polytope's lattice Laplace partition function. For a query-dependent point inside a learnable polytope, the log-partition gradient is the expected lattice direction under a Gibbs distribution, while its Hessian is a covariance matrix that supplies curvature-aware features.
Replace softmax attention or dense MoE routing with a normalized Rayleigh–Jeans distribution over tokens or experts. If an item's energy is close to the chemical potential, its probability becomes disproportionately large, creating controllable low-energy condensation instead of the exponentially smooth allocation produced by softmax.
Construct a candidate feature for every edge pair or structured token pair, then retain a numerically independent subset under a feature-Jacobian matroid. The neural layer computes only the selected interactions, preserving directions that add new information rather than pruning solely by magnitude or attention score.
Replace a generic three-input concatenation MLP with a permutation-symmetric mixer built from the four signed combinations x+y-z, x-y+z, -x+y+z, and -x-y-z. Apply a shared truncated exponential to these combinations and aggregate symmetric pairwise products, producing controlled quadratic and higher-order interactions without materializing a full trilinear tensor.
Construct a sparse attention mask from a fixed regular candidate graph and one scalar random label per token, retaining edge $(u,v)$ when $x_u+x_v\geq\tau$. Unlike independent random pruning, this produces correlated neighborhoods and a controllable distribution of token degrees, potentially giving some tokens broad receptive fields while retaining a fixed sparse budget.