Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Attach finite Hankel positive-semidefiniteness penalties to a neural model that predicts scalar moments, cumulants, or beta-distribution parameters. The exact beta inequality supplies a very cheap first-stage barrier, while eigenvalue penalties on larger Hankel matrices constrain higher-order structure.
Replace or supplement spectral-norm and Frobenius penalties on neural-network weight matrices with the Hardy-type norm given by the geometric mean of their gains over uniformly sampled unit directions. This penalizes typical multiplicative amplification through a logarithmic average, while the paper's theorem guarantees that the resulting quantity is a true norm rather than an ad hoc nonconvex statistic.
Represent each bias-free hard MoE routing region as a polyhedral cone in router feature space and regularize its estimated conic intrinsic-volume sequence. The penalty enforces the paper's strengthened log-concavity inequality, preventing routing regions from having implausible concentration at isolated face dimensions and potentially reducing unstable expert starvation.
Construct augmented sequences by tiling long contexts with large finite blocks sampled from a library whose local-pattern frequencies match a target dataset, replacing only block interiors and leaving boundary zones untouched. This produces globally coherent synthetic contexts while controlling the distortion of short-range statistics through an explicit boundary-to-volume ratio.
Use the calibrated compact-support maximum-entropy law as a latent prior or representation regularizer in a VAE or autoencoder. Unlike a Gaussian prior, it prevents latent codes from drifting arbitrarily far while retaining explicitly controlled mean and covariance.
Estimate the spatial distribution of minibatch embeddings using normalized residuals, then use the resulting spatial depth as a bounded confidence weight on each example's loss. Examples whose embeddings are spatially central receive near-unit weight, while isolated or adversarial examples are automatically downweighted without estimating covariance matrices or choosing a dimension-dependent bandwidth.
Represent MoE experts as leaves of a balanced ternary tree and regularize the hierarchical boundary of each expert's assignment mask. At fixed routing mass x, the ternary martingale isoperimetric theorem supplies the explicit minimum one-variation T_3(x), so the router can be penalized according to an occupancy-dependent profile rather than a uniform parent-child disagreement cost. This should favor coherent, stable routing regions while preventing small expert supports from obtaining…
Replace heuristic moving-average thresholds for a nonnegative neural-network quantity with an exact finite-sample p-value computed from a batch of independent observations. Use the p-value to stop training, trigger a learning-rate reduction, or reject a model whose expected loss or safety cost exceeds a prescribed threshold, without assuming bounded, Gaussian, or identically distributed observations.
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.
Add a Microscopic Dynamical Entropy-inspired regularizer to a VAE or sequential world model. Instead of maximizing only the entropy of the latent marginal, maximize latent marginal entropy plus an estimate of the log-volume of unresolved variables compatible with each latent state, thereby preferring representations that summarize predictable macroscopic structure while assigning nuisance detail to the residual channel.
Construct two latent variables X and Y with exactly the same marginal distribution, while forcing their difference X-Y to follow a chosen centered noise or residual law. Insert the pair into a residual, VAE, or diffusion block so that the model receives the desired perturbation without changing the marginal latent distribution at either endpoint. This creates a controlled alternative to independently sampled noise, especially when marginal drift in repeated stochastic layers is harmful.
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.
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.
Represent a neural network's categorical output over a rooted tree using cumulative probability mass on each rooted subtree. Train pairs of examples with a stochastic-dominance loss that compares these subtree masses, avoiding enumeration of all upper sets and making hierarchical monotonicity explicit. This is suitable for taxonomies, severity levels, hierarchical intents, and structured world-model states.
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.
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.
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.
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 graph-derived conditional moment penalty to a neural representation or predictor. For each nested Markov constraint represented after fixing variables in R, residualize functions of (X,Z) with respect to Z under the post-fixing distribution and penalize their weighted correlation with functions of (Y,Z). This directly targets the equality constraint and can be more informative than an unconditional decorrelation penalty.
Regularize a network using the weak-L^p tail of scale-normalized feature differences between an input and sampled perturbations, instead of averaging all pairwise differences with an ordinary L^p penalty. The weak norm emphasizes persistent high local sensitivities while being less dominated by a single extreme pair than a hard maximum.
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.
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.
Replace explicitly stored independent random positional features with deterministic multiplicative phase features generated from a small table of random phases indexed by primes. Restrict positions to integers whose prime factors exceed a slowly growing threshold, because the paper's central-limit result says periodic weighted sums over these rough integers recover Gaussian behavior despite strong multiplicative dependence.
Exploit the paper's nested obstruction hierarchy by applying cheap low-order Hankel tests to every example and evaluating larger matrices only for outputs near the current feasibility boundary. This turns higher-order structural validation into an adaptive curriculum rather than an always-on expensive eigendecomposition.