Solves: Stability

Machine-learning ideas tagged Stability in the Solves taxonomy of the Math2NN corpus.

2414 ideas found

Unverified 2026

Elliptic Low-Oscillation Feature Layer

Construct a spatially varying diffusion layer whose coefficient matrix is explicitly uniformly elliptic and whose local mean oscillation is penalized. Use it inside an implicit residual block, so the learned operator remains a controlled perturbation of a constant-coefficient elliptic operator rather than becoming an unstable collection of unrelated local filters.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Regularity for Elliptic Equations with Coefficients of Small Mean Oscillation arXiv:2608.10813
Unverified 2026

Authority-Limited Removal Gating

Construct a branching residual network whose active computational paths reproduce according to a fixed offspring/connectivity law, while a controller can only remove paths using an age- or depth-dependent hazard \(u(a)\). Use the resulting bound as a diagnostic and gating schedule: removal can suppress unstable activity and reduce compute, but it should not be expected to cross the reproduction-driven propagation barrier unless the network's expansion operator is also changed.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Removal-Only Actuation in Age-Structured Branching Populations: Fundamental Limits of Equilibrium Placement arXiv:2608.10641
Unverified 2026

Lorentzian coefficient router

Represent a small expert router or attention interaction by a homogeneous polynomial with nonnegative coefficients, then penalize violations of the Lorentzian Hessian signature on degree-two derivative slices. Initialize or warm-start the coefficient tensor from a normalized skew-Schur coefficient array, which the paper identifies as a realizable volume polynomial and therefore a structurally valid Lorentzian point.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Richardson volume models for skew Schur and skew Schur $P/Q$-functions arXiv:2608.10516
Unverified 2026

Subgaussian orthogonal feature basis

Add a learnable orthogonal rotation to a hidden representation and train it to make every channel projection have a small ψ2/L2 ratio. Unlike variance normalization, this explicitly suppresses directions with unusually heavy empirical tails while preserving the total quadratic energy of the representation.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Geometry of the subgaussian body of an isotropic convex body arXiv:2608.10241
Unverified 2026

Fluctuation-Floor Regularizer for Learned Samplers

Add a trajectory-level consistency constraint to a diffusion or Markov generative model by comparing the likelihood of each sampled path with the likelihood of its reversed path. The constraint uses the paper's sharp fluctuation floor to detect when a model produces too many strongly backward-looking trajectories or hides directional mismatch in a small number of extreme events. This is a regularizer and diagnostic for learned stochastic dynamics, not a replacement for the generative likelihood…

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Bounds for Apparent Second-Law Violations in Quantum Trajectories arXiv:2608.10118
Unverified 2026

Parity-Conserving Reaction-Diffusion Memory

Replace unconstrained recurrent-state decay with a one-dimensional latent defect field whose states evolve by local diffusion and pair reactions. Defects can move over long distances and persist, while creation and removal occur only in pairs, giving the memory a structured cancellation mechanism that is potentially better suited to delayed-event and parity-like sequence dependencies than a standard GRU or diagonal SSM.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Kinetics of sliding-window quantum error correction arXiv:2608.10081
Unverified 2026

Birkhoff Modular Mask Regularizer

Represent structured neural masks or routing states as order ideals of a finite prerequisite poset, then use a modular score whose exact minimizers are a desired decomposition-closed family of valid configurations. This replaces many pairwise constraint penalties with one additive potential that gives zero cost to every intended valid state and positive cost to invalid intermediate states.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Decomposition-Closed Sublattices as Minimizer Sets of Modular Functions over Distributive Lattices arXiv:2608.10026
Unverified 2026

Asymmetry-Aware Bochner–Riesz Graph Filter

Replace a sharp graph-Laplacian spectral filter with a Bochner–Riesz filter whose smoothness exponent increases when the graph contains regions with different effective dimensions. Estimate the largest local dimension and dimension gap from neighborhood growth, then choose the exponent above both the classical spectral threshold and the asymmetric obstruction threshold. This should suppress unstable high-frequency mixing in heterogeneous graphs while preserving more low-frequency signal than…

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Herz versus Fefferman: Symmetric and asymmetric Bochner--Riesz theory arXiv:2608.09247
Unverified 2026

Isochronous Emden recurrent cell

Replace the linear state transition in a recurrent layer with a bank of odd-power modified Emden oscillators. The nonlinear terms provide state-dependent interactions while the paper's odd-q result preserves period T=2π/ω independently of amplitude, giving the model a stable internal phase clock for long sequences. External inputs should modulate the oscillator through a bounded forcing or readout gate rather than directly destroying the autonomous isochronous dynamics.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Isochronous and underdamped waveforms of modified Emden oscillators arXiv:2608.09008
Unverified 2026

Prescribed-Order Equilibrium Vector Field

Constrain a neural vector field to vanish to order at least k at a designated anchor state c. The network predicts smooth coefficient functions, while a fixed degree-k monomial gate supplies the required vanishing behavior. This exactly enforces the equilibrium and suppresses all local drift terms below order k, potentially improving stability and extrapolation near known rest states.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Finite-Rank Lie Algebroids for Singular Foliations of Prescribed Vanishing Order arXiv:2608.07351
Unverified 2026

Mean-Curvature Relaxation Layer

Insert a small number of differentiable graphical mean-curvature-flow steps between a neural network's raw vector-field prediction and its task loss. The relaxation performs geometry-aware smoothing rather than isotropic Gaussian smoothing, and it can enforce fixed boundary values after every step.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Well-posedness for the mean curvature flow on the half-space and on bounded domains arXiv:2608.08901
Unverified 2026

Kemeny-Regularized Message Passing

Regularize a learned GNN adjacency so that its random walk mixes rapidly, reducing graph bottlenecks and isolated regions that make information propagation inefficient. Use a thresholded penalty rather than minimizing Kemeny's constant to zero, because excessively fast mixing can produce oversmoothing.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: On two conjectures concerning Kemeny's constant of graphs arXiv:2608.08797
Unverified 2026

Critical weak-spectrum penalty for area features

Apply a weak-trace spectral constraint to the covariance of antisymmetric second-order features, encouraging a 1/i eigenvalue envelope rather than forcing a finite trace norm. This targets the paper's sharp logarithmic Ky Fan behavior and may preserve useful long-tail interaction directions that nuclear-norm regularization would remove.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Infinite-Dimensional Levy Area: Probability-Selected Critical Geometry and Sharp Spectral Selection arXiv:2608.08756
Unverified 2026

Sharp fractional interpolation envelope for feature maps

Add a scale-invariant Gagliardo–Nirenberg ratio penalty to intermediate CNN or spatial neural-network feature maps. The penalty discourages representations with unusually large low-order fractional gradients relative to their amplitude and high-order energy, providing a single mathematically coupled constraint instead of separately weighted total-variation and Sobolev penalties. Apply it only to selected layers and estimate the reference sharp constant from clean baseline activations.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Sharp homogeneous Gagliardo--Nirenberg inequalities with applications to normalized solutions for a generalized MMT-type equation arXiv:2608.08686
Unverified 2026

Spectral-Gap Count Augmentation

Replace independent perturbations of a bag-of-events or histogram input by a Markov augmentation that resamples overlapping-window count vectors according to a stationary conditional kernel. The augmentation preserves realistic correlations induced by a learned reversible transition matrix and has a measurable mixing-rate guarantee, preventing an arbitrary augmentation chain from producing highly correlated or unstable samples.

Useful5/10
Difficulty7/10
Novelty8/10
Paper: Conditionally Resampled Sliding-Window Count Kernels: Spectral-Gap Bounds and Poincaré Inequalities arXiv:2608.08678
Unverified 2026

Adaptive Isotropic Latent Coordinates

Add the paper's joint shape-and-mass distortion objective to a neural coordinate map whose output is a three-dimensional latent representation. Penalize anisotropic local Jacobians through a log-distortion term and penalize nonuniform latent occupancy through a density-gradient term, while learning the radii of an ellipsoidal latent target domain. This should discourage folds and collapsed regions without forcing every dataset into a fixed spherical latent prior.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Adaptive Volumetric Parameterization of Simply Connected 3-Manifolds with Applications arXiv:2608.08672
Unverified 2026

Random-cluster anti-correlated routing

Replace independent Bernoulli branch dropout in a tree-structured mixture or hierarchical MLP with connectivity gates sampled from a q<1 wired random-cluster model. The q<1 law provides conditional negative association across branches, so increasing statistics of disjoint branches have nonpositive covariance; this should reduce redundant expert activation while preserving structured stochastic exploration.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: The $q<1$ Random-Cluster Model on Wired Trees: Uniqueness and Negative Dependence arXiv:2608.08565
Unverified 2026

Lexicographic spectral activation

Replace an ordinary elementwise nonlinearity on a learned Hermitian matrix with a matrix function f(A), while supplying exact Jacobian-vector and Hessian-vector products through the lexicographic divided-difference formula. This gives a principled spectral layer for covariance features, graph operators, attention kernels, or matrix-valued embeddings, particularly when perturbation matrices do not commute and eigenvalues are repeated or nearly repeated.

Useful5/10
Difficulty5/10
Novelty5/10
Paper: Lexicographic functional calculus and its application to functional calculus calculus arXiv:2608.08404
Unverified 2026

Seven-Factor Stochastic Transition Layer

Parameterize a learned 3-state transition operator as a product of at most seven elementary row-stochastic matrices rather than learning its nine entries independently. Each factor performs one convex pull-in of row i toward row j, so every intermediate and final matrix remains row-stochastic and the layer has a sparse, bounded-depth interpretation.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Bang--bang representation of $3\times 3$ embeddable stochastic matrices arXiv:2608.08242
Unverified 2026

Monotone Hardy Mixer

Replace a learned causal mixing profile by a monotone profile followed by a prefix-average Hardy mixer. The monotonicity constraint makes the mixer provably non-degenerate in the BMO sense: localized variation in the profile cannot be reduced below a calibrated factor by prefix averaging. This is a cheap alternative to dense causal attention for tasks where importance or state profiles are expected to decay along sequence position.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: The sharp reverse Hardy inequality in BMO for nonincreasing functions arXiv:2608.08093
Unverified 2026

Shape-profile dependence regularizer

Regularize a neural model using the shape function of two learned variables rather than a single mutual-information scalar. For a pair of representations $(X,Y)$, evaluate the profile on a grid of $(\alpha,\beta)$ values and optimize a target profile or penalize undesirable lower-left-triangle dependence. The auxiliary variable $W$ is produced by a small adversarial encoder, approximating the supremum in the definition and thereby finding the most informative conditional decomposition of the…

Useful5/10
Difficulty7/10
Novelty6/10
Paper: Shapes and Norms of Random Pairs arXiv:2608.08039
Unverified 2026

Rotation-Invariant Turning-Angle Matching

Add a trajectory-level loss that matches the empirical distribution of consecutive velocity turning angles between observed and generated sequences. Because turning angles are unchanged by a common rotation of all coordinates, the model is forced to reproduce hidden anisotropic and temporally correlated motion without being given a fixed laboratory-frame orientation.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Turning angle analysis reveals hidden anisotropies in the anomalous diffusion of molecules in live cells arXiv:2608.07975
Unverified 2026

Least-Fixed-Set Propagation for Recurrent Networks

Represent the hidden state of a recurrent or implicit neural block by a convex reachable set and encode its recursive constraints as containment inequalities rather than unrolling a fixed number of steps. Eliminate the set variables to obtain the smallest representable invariant set, which can be used as a tighter robustness certificate, a training regularizer, or a principled initialization for equilibrium solvers.

Useful5/10
Difficulty7/10
Novelty6/10
Paper: Solving polynomial inequalities over spaces of convex sets and applications arXiv:2608.07794
Unverified 2026

Plucker Compound-Rank Regularizer

Construct a symmetric feature-interaction or Jacobian matrix A_theta whose desired rank is t, then regularize its t-th compound matrix toward rank one. This transfers the paper's identity that a rank-t matrix has a rank-one t-th compound, while the rank-one factor encodes Plucker coordinates of the kernel subspace.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Brehm-Wintner-Conley Dimension, Plücker Coordinates, and Generalized Dziobek-Williams Equations for Central Configurations arXiv:2608.07771