Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Regularize learned low-dimensional embeddings or MoE prototypes with an aggregation-diffusion energy. The attractive term encourages compact, semantically coherent groups, while porous-medium diffusion creates density-dependent pressure that prevents points from collapsing into singular clusters.
Replace independently sampled random-walk paths used for GNN neighbor or subgraph sampling by persistent rotor walks on the training graph. Each node stores a pointer into a fixed cyclic ordering of its outgoing neighbors; every visit advances the pointer and selects the next neighbor, producing deterministic coverage with no repeated random choices. Use several short rotor trajectories per seed and periodically reinitialize only the rotors in an encountered subgraph.
Add a mean-field stochastic binary recurrent layer with an explicit susceptibility controller. The layer estimates the response statistic \(\chi=\beta^2N^{-1}\sum_i\operatorname{sech}^4(u_i)\) and either penalizes or clips it below \(1-\delta\), preventing the high-gain regime in which replicas with identical weights develop strongly divergent states. The expected benefit is more stable long-horizon recurrence and lower variance across stochastic forward passes.
Use the hysteresis threshold as a regularizer for attractor diversity. Estimate how many initial states converge to each fixed point and select thresholds that maximize basin entropy or penalize domination by one attractor, reducing attractor collapse in discrete recurrent classifiers and memory modules.
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.
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.
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 \(I+T\).
Represent selected hidden features as z = sqrt(N) exp(i theta), with a persistent phase and an explicitly stochastic amplitude. Regularize the ratio between coherent power |E[z]|^2 and total power E[|z|^2] toward the condensate prediction pi/4, while optionally matching higher amplitude moments.
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.