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 hidden activations or per-example gradients with a discrete version of the paper's Z_E^2 norm. Apply an E-norm to the largest fraction of coordinates and an L2 norm to the remaining tail, allowing the model to preserve a few large responses while discouraging widespread heavy-tailed noise.
Do not rely on a weak-Schatten or weak-Lp quasi-norm as the sole safety metric for a two-sided neural operator. Track the complete singular-value product and use a strong Schatten penalty when logarithmic spectral ordering must correspond to a reliable notion of operator complexity.
Use a pressure objective to select expert-routing distributions by balancing task reward against route entropy, rather than optimizing task loss alone. The resulting router behaves like an equilibrium-state estimator: it should retain multiple high-performing branches when their combined entropy outweighs the advantage of a single branch.
Add an auxiliary loss that makes selected representation coordinates insensitive to all subsets of fewer than d variables while retaining a d-way parity statistic. The objective discourages the network from solving a task through pairwise shortcuts and explicitly rewards a controlled high-order interaction.
Add a low-rank control perturbation to each optimizer block so that the next-step parameter dynamics compensate for growth of selected normalized perturbation directions. The control is computed by least squares from Jacobian-vector products, with a trust-region penalty limiting its stochastic cost; unlike isotropic weight decay, it targets directional instability while preserving directions that are already contracting.
Construct a four-branch neural interaction whose inputs are affine projections of a two-dimensional latent coordinate and whose output is the weighted product prescribed by the theorem. Normalize this product by the corresponding branch L1 masses, yielding a feature whose mixed norm is theoretically bounded up to the inequality constant. Use the normalized interaction as an architecture component or as a replacement for an unconstrained multiplicative fusion layer.
When a neural field learns power-law exponents, penalize exponent configurations whose Newton support violates the paper's finite-distance accessibility condition. This discourages combinations of exponents that create excessively strong joint singularities while preserving anisotropic scaling when it is supported by the data.
Replace an unconstrained residual adapter around a neural linear layer by a contractive operator whose action interpolates observed feature perturbations and remains bounded in operator norm. The adapter is trained adversarially over this structured uncertainty set, producing perturbations tied to empirical feature data rather than arbitrary isotropic noise.
Insert a positivity-preserving fractional Schrödinger resolvent into a 1D neural sequence block. Given a nonnegative learned potential V, the layer transforms an input signal f using V^a(-Delta+V)^(-a)f, allowing the network to learn where to smooth or suppress features while retaining an L1 bound independent of the potential magnitude. Use a in (0,1] as a fixed hyperparameter or a clipped learned scalar.
Use the lifted convex hull as a training-time regularizer for pairs of nonnegative neural features, encouraging their empirical second- and third-order interaction statistics to lie in the paper's moment cone. This constrains correlations, squares, and cubic cross-moments jointly through PSD inequalities instead of merely penalizing large activations.
Apply a weighted Caffarelli–Kohn–Nirenberg deficit to selected intermediate feature channels. The penalty discourages features that obtain large weighted responses only by becoming sharply localized or highly sensitive to small input perturbations. It can be evaluated with input-Jacobian estimates and added to the ordinary task loss.
Regularize probability-valued network outputs in the square-root representation rather than directly penalizing density curvature. This suppresses sharp oscillations while avoiding the severe scaling of derivative penalties involving \(\nabla\rho/\rho\) near vacuum regions.
Replace the symmetric Euclidean contrastive loss between embeddings with a two-point quadratic contrast whose displacement is generated by a local affine connection and measured using the metric at the source endpoint. Because the metric and transport need not be compatible, the loss can be asymmetric, allowing the model to represent directional relations between examples.
Replace ordinary isotropic residual noise in a normalized continuous-depth block with projected Brownian forcing on the unit sphere. Apply a shared random symmetric quadratic drift to all tokens, plus a small token-specific tangent perturbation; the shared term preserves structured antipodal dynamics while the independent term removes persistent symmetry and cluster degeneracy. This is intended as a controlled stochastic regularizer, not merely additive Gaussian noise.
Replace ordinary additive or multiplicative activation noise with a nonnegative count-valued perturbation generated by the Hermite operator kernel. For a nonnegative feature x, sample an integer N whose distribution is exactly the operator's weight sequence and feed N/n to the next layer; the parameter alpha controls an additional even-jump component and therefore changes the noise geometry independently of the ordinary Poisson component.
Add a metric-learning loss whose local geometry changes according to several learned or supplied boundary coordinates. Use a product conformal factor when violations of multiple constraints should accumulate, or a sum conformal factor when the most severe constraint should dominate; on a face where several coordinates vanish, impose the corresponding snowflake exponent on tangential distances.
For a neural model predicting a scalar response as a function of a continuous dynamical parameter, replace an unconstrained MLP output head by an analyticity-constrained spectral head. Train it on observations covering a positive-measure subset of the parameter interval and regularize the remaining coefficients so that the learned response satisfies a quasi-analytic derivative-growth bound; the intended benefit is reliable continuation from sparse parameter coverage rather than ordinary…
Apply a trainable scalar gate entrywise to a Min/Max structured affinity or covariance matrix while enforcing that the gate is nonnegative, nondecreasing, and convex. This preserves Loewner ordering on the structured cone and avoids unconstrained elementwise nonlinearities that can destroy PSD or order relations.
Train a neural predictor with a blended objective containing both ordinary outcome prediction error and downstream decision regret. The prediction term prevents a decision-focused objective from accepting degenerate predictors that induce the same in-sample decision, while the regret term biases the network toward errors that matter for the actual optimization problem.
Use multiplier bootstrap on minibatch activation covariances to determine whether a large top eigenvalue is a genuine representation direction or merely a high-dimensional bulk fluctuation. When a spike is repeatedly significant, apply a low-rank whitening or shrinkage correction to that activation subspace; otherwise leave the layer unchanged, avoiding destructive whitening of ordinary bulk variation.
Represent the eight experts or channels in a block as the vertices of a 3-bit hypercube and compute their average nonnegative routing masses. Add a regularizer that rewards a large ratio between the product of the six coordinate-facet sums and the mixed triple/pair polynomial from the theorem. This explicitly encourages routing distributions that remain visible under all three binary projections, rather than merely maximizing entropy or balancing experts marginally.
Put a gradient-Gibbs prior on differences between connected neural parameters rather than on individual parameters, and evolve the parameters with Langevin steps generated from randomly selected strictly convex component energies. The aggregate regularizer may be non-convex, but every sampled component has controlled curvature and outward drift, providing a practical stability mechanism for noisy training.
Replace a polynomial layer's single-replica output statistics with a finite fingerprint computed from several correlated Gaussian replicas. Train the fingerprint to be invariant under orthogonal reparameterizations while remaining discriminative between genuinely different polynomial maps, preventing models from collapsing distinct tensor functions that have identical marginal output laws. This is a practical symmetry-aware regularizer or auxiliary embedding for tensorized MLPs and polynomial…
Constrain an embedding table to the unit sphere and penalize repeated or nearly repeated pair sums. This discourages additive quadruples a+b approximately equal to c+d, reducing unwanted linear structure and making distinct tokens less interchangeable under downstream composition. The theorem provides a geometric target: on a sphere, the affine-line concentration factor is bounded by two, so exact additive energy should scale close to n squared rather than the much larger values produced by…