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 fractional oscillation penalty to scalar functions produced by a neural network on an ordered grid. Unlike a derivative penalty, this remains meaningful for nonsmooth or nowhere-differentiable outputs and interpolates between total-variation-like behavior and Sobolev-like smoothness.
Insert a rearrangement operation on scalar feature maps sampled along an ordered coordinate such as time, spatial position, or a neural-field input grid. The operation sorts values into non-increasing order, preserving the empirical histogram exactly while provably not increasing the Riesz fractional variation in the ideal one-dimensional continuous setting.
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.
Build an attention or positive-mixture module whose output ratio at two control settings is provably monotone in an ordered index such as token distance, retrieval rank, or discretized uncertainty. Use normalized-positive-series identities to replace an unstable quotient derivative with a difference of expectations, and penalize violations of the resulting stochastic-order condition during training.
Construct a robust central region of each class or domain embedding cloud by intersecting halfspaces whose discarded cap mass is at most a prescribed fraction. Use this floating-body region to define prototypes or consistency targets, suppressing one-sided outliers without assuming Gaussian covariance structure. The centerpoint level 1/(d+1) provides a principled default depth parameter.
Calibrate the maximum attention logit in each head against the log-correlated extreme-value law instead of applying fixed clipping or a fixed max-norm penalty. Penalize only maxima that exceed the predicted log N minus three-quarter log log N baseline by an unusually large order-one fluctuation, allowing ordinary sharp attention while suppressing rare pathological spikes.
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.
Apply the paper's sharp sumset lower bound to the active discrete supports of multiple additive branches in a sparse neural layer. Penalize cases where the support of the combined output is smaller than the mathematically guaranteed minimum implied by the branch supports, discouraging destructive overlap and representational collapse.
Estimate how often a representation lies on a separating hyperplane for alternative separable dichotomies, and use this quantity as a boundary-concentration penalty. Unlike a single classifier margin, the score measures whether many admissible separators consider the point ambiguous.
For two monotone prediction heads receiving binary features, penalize cases where their covariance is smaller than the sharp degree-weighted collision of their Fourier spectra. This discourages uncontrolled agreement on high-order interaction patterns while preserving low-order shared structure, and can be used either as a constraint or as a diagnostic for monotone multi-task models.
Add a differentiable penalty to a graph generator or graph predictor when its soft higher-order clique density violates the sharp lower bound implied by its lower-order clique density. The regularizer encourages generated graphs to have mathematically consistent motif statistics without hard-discretizing the predicted adjacency matrix.
Measure the local geometric compatibility of q latent distributions produced by different views, augmentations, environments, or trajectory models using the paper's co-dimension. Penalize excessive cross-branch co-dimension over a range of radii while preserving per-branch variance and covariance rank to prevent representation collapse.
Represent entities, tokens, or graph nodes by learnable rays subject to orthogonality constraints on prescribed hypergraph contexts. In addition to enforcing orthogonality within each context, penalize distinct vertices that become collinear, because contextual orthogonality alone can permit or force geometric collapse. This creates a structured embedding layer for graph neural networks or context-aware attention.
Replace the usual uniform expert-load target in sparse MoE training with a random, heavy-tailed capacity allocation generated by a conditioned Poisson point process. The constant profile reproduces a Poisson–Dirichlet-like allocation, while a profile such as \(\phi_\gamma(x)=1+e^{-\beta\gamma x}\) deliberately changes the frequency of large versus small expert allocations.
Add a finite-state message-passing layer that tracks local configurations corresponding to perfect edge domination or dominating induced matchings instead of transmitting unconstrained node embeddings alone. On graphs with a tree, series-parallel, or small-separator decomposition, the layer produces an exact or differentiable partition function over globally valid edge configurations, which can be used as node features, an auxiliary loss, or a structural prior.
Build a decoder \(F:\mathbb{R}^m\to\mathbb{R}^N\) whose latent-coordinate derivatives are approximately horizontal, meaning they annihilate a prescribed one-form \(\lambda\). When \(\lambda\wedge d\lambda=0\), use local chart-wise training or Jacobian projection to exploit the paper's Lipschitz extension regime and obtain smoother, geometrically valid interpolations between observed boundary samples.
Use the paper's asymptotic null law to decide when two minibatch covariance structures are statistically distinguishable, rather than applying a fixed covariance-matching weight throughout training. This creates a confidence-gated regularizer that is strong when discrepancies exceed sampling noise and weak when the observed difference is compatible with finite-batch variability.
Add a boundary-aware nonlocal regularizer to hidden-state sequences by subtracting the sharp Hardy weight from the fractional discrete-Laplacian energy. The resulting penalty is provably nonnegative on finite sequences under zero-padding at the left boundary, while its position-dependent Gamma-ratio weight concentrates protection near the sequence boundary.
Add an inverse-capacitary-distance penalty to coordinate-network outputs near complex forbidden sets, rather than using only Euclidean distance-to-boundary weighting. The penalty is theoretically compatible with the network's spatial Dirichlet energy: it suppresses large values near obstacles while the gradient penalty controls the weighted singularity, even when the obstacle is thin, perforated, or fractal-like.
Add a bank of quadratic features encoding tangent contact with the reciprocal manifold x1 x2 = 1, rather than forcing a generic MLP to discover this interaction from arbitrary monomials. For positive bounded feature pairs, each feature is nonnegative and becomes exactly zero at a selected reciprocal operating point. The module can be used either as an input feature expansion or as a regularizer encouraging learned gates and scales to follow a reciprocal geometry.
Parameterize a complex neural feature F(z) as a low-degree holomorphic polynomial and train it from magnitude-squared observations using a Gaussian-weighted residual to the best constant intensity baseline. The paper's coercivity inequality makes this more than an observation-space loss: small intensity variation certifiably bounds the error of the phase-invariant squared feature F^2-F(0)^2. Use the bound as a regularizer or as a replacement for an unavailable complex-target loss in…
Replace ordinary summation of several matrix-valued residual branches by a concave spectral aggregation: form the branch sum, take its absolute value, and apply a nonnegative concave function to singular values. The paper's transfer theorem predicts that the sharp Schatten-norm amplification constant is no worse than the corresponding linear Lee-type constant, while square-root, logarithmic, and capped maps suppress dominant singular directions.