Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Use a spherical-design codebook and the paper's polar slack factorization to create a nonnegative geometric interaction bias for attention or expert routing. The resulting kernel is generated by a rank-one term and a rank-at-most-d term, and entries close to zero can define a structured sparse mask instead of relying only on learned top-k selection.
Replace Euclidean momentum for selected neural parameters with a mirror or Bregman update, while using the paper's accelerated Newton direction for the objective step. Entropy geometry is especially suitable for softmax MoE routers, while Euclidean or log-barrier geometries can be used for unconstrained or positive parameters.
Prune redundant attention heads using separate similarity scores for sink behavior and content routing. Two heads are considered safely redundant only when their normalized content compositions are close in Aitchison distance and their sink-mass trajectories are also close, avoiding pruning decisions dominated by a shared sink token.
Distill a teacher's attention into a student by matching sink mass and the normalized content distribution as separate targets rather than applying one KL divergence to the entire attention row. Use the Aitchison distance on the content composition, which compares relative token allocation and prevents a large common sink probability from overwhelming differences between content tokens.
Add global directed-curvature features to every node in a graph neural network or directed graph transformer. The features distinguish how a node functions as a source versus a destination in the graph's asymmetric metric, potentially exposing bottlenecks, hubs, sinks, and structurally central nodes that local message passing cannot identify.
Use a learned asymmetric Finsler-like cost instead of the symmetric Euclidean distance in attention logits. The metric has a Riemannian quadratic part and a directional drift term, while a differentiable barrier enforces the strong-convexity condition derived for the paper's extended $(\alpha,\beta)$-metrics. This lets each attention head prefer one direction in feature space without producing pathological, non-convex distance landscapes.
Replace dense grid tokens or global spectral features with coefficients of compactly supported kernels centered on a nested hierarchy of spatial points. Encode an input field into coarse-to-fine coefficients, apply a neural map to those coefficients, and decode the predicted coefficients at arbitrary query locations; the contribution from each level provides an explicit multiscale output decomposition.