Solves: Stability

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

2414 ideas found

Unverified 2026

Precommitment Information Gate

Add a causal gate to a neural safe-RL controller that distinguishes between evidence observed before a potentially irreversible action and evidence generated by that action itself. The policy may switch from a conservative controller to a model-specific aggressive controller only when the precommitment likelihood ratio against every dangerous alternative exceeds a threshold; otherwise it must choose an action with a verified safe continuation.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: When Can Safe Controllers Adapt? Information before Commitment arXiv:2607.16895
Unverified 2026

Regular Linear Hypergraph Attention

Construct attention groups as hyperedges of a linear r-uniform hypergraph: every pair of tokens is allowed to share at most one group, while each token participates in approximately the same number of groups. Apply local attention inside each group and aggregate the outputs across groups. The construction inherits the paper's sharp capacity bound and prevents both redundant pair interactions and high-degree token hubs.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Linear Turán Numbers of Uniform Hypertrees arXiv:2607.16854
Unverified 2026

Cycle-certified nonnegative rank-one attention

Represent a nonnegative attention or routing score matrix by two nonnegative vectors, X = uv^T, and learn only entries on a sparse bipartite graph of important query-key or token-expert interactions. Complete the remaining entries multiplicatively and monitor cycle residuals as a certificate of whether the sparse representation is compatible with rank one. Use local ratio violations to trigger additional edges or relax the rank-one approximation only where needed.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Tight Conic Relaxations for Rank-one Doubly Nonnegative Matrix Completion arXiv:2607.16796
Unverified 2026

Rigid-Motion-Quotient Covariance Loss

Add a distribution-level loss that compares minibatch embeddings only through the square roots of their ordered covariance eigenvalues, ignoring global translation and rotation of the embedding coordinate system. This implements the Gaussian specialization of the paper’s Procrustes-Wasserstein geometry and is useful when two embedding clouds are semantically equivalent up to a rigid change of coordinates.

Useful6/10
Difficulty4/10
Novelty5/10
Paper: Dynamical Optimal Transport with $\mathfrak{so}(d)$-Invariance: From Theory to Computation arXiv:2607.16782
Unverified 2026

Concave Heterogeneous Prototype Layer

Replace ordinary k-means-style prototype assignment with a distance-decay capture layer whose scale varies across samples, tokens, or classes. Train with a cooperative concave surrogate over prototype centers and anneal toward hard nearest-prototype assignment; this explicitly preserves useful gradients for multiple nearby prototypes while retaining sparse facility-like behavior at inference.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: When Is Heterogeneous Distance-Decay Facility Location Tractable? A Structural Classification, Exact Methods, and a Real-World Study arXiv:2607.16764
Unverified 2026

All-Cut Schatten Control for Polynomial Layers

Replace ordinary Frobenius or spectral-norm control of a tensorized multilinear layer by a sampled approximation to its oriented Schatten profile, the maximum Schatten norm of every input-output flattening. Regularizing this profile should control Gaussian or randomized polynomial activations uniformly over hidden width and tensor contraction pattern, reducing exploding activations and making higher-order layers easier to scale.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Algebraic Transfer for Operator-Valued Gaussian Chaoses:Oriented Schatten Profiles and Singular Wick Multipliers arXiv:2607.16724
Unverified 2026

De-floored low-rank feature preconditioner

Replace the usual inverse-eigenvalue weights in a low-rank feature-covariance preconditioner by inverse weights with an estimated isotropic floor subtracted. Retain only the top r eigendirections and require every corrected denominator to exceed a margin, preventing the shifted inverse from approaching a pole. This should undo systematic under-updating of predictive directions when many weak feature directions inflate the empirical covariance.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: De-floored Principal Component Regression: When Rank Selection Alone Is Insufficient for Prediction arXiv:2607.16638
Unverified 2026

Hysteretic Continuation Controller

Use the external field H as a slowly swept control variable for a neural module, loss coefficient, or optimizer gain, and deliberately retain the resulting branch memory instead of replacing it with an instantaneous equilibrium update. Forward and backward sweeps produce a hysteresis loop whose shape diagnoses first-order-like training transitions, while controlled disorder changes the loop area and can suppress harmful branch dependence. This supplies a continuation-based curriculum or…

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Glauber dynamics phase transitions in athermal random field Blume-Capel and Blume-Emery-Grifitths models arXiv:2607.16561
Unverified 2026

Dyson Diagonal Scaling for Directed Message Passing

Replace ordinary row-degree or symmetric normalization in a directed graph neural network with a nonlinear Dyson scaling. For a nonnegative directed adjacency matrix A, solve a positive vector equation and propagate with B = D A D, where D is the diagonal matrix of the solution. The resulting operator has row sums strictly below one, giving an explicit bound against exploding directed message propagation while retaining asymmetric edge information.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Non-symmetric vector dyson equations arXiv:2607.16333
Unverified 2026

C1 Homogeneous Lyapunov Critic

For a neural ODE or recurrent state update, learn a positive-definite degree-two homogeneous Lyapunov function that is only C1, rather than restricting the certificate to polynomials or analytic neural networks. Parameterize its angular dependence with a positive spline or softplus mixture, and train it to decrease along the learned vector field; this can certify stable dynamics that polynomial Lyapunov searches systematically miss.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: A Globally Asymptotically Stable Planar Homogeneous Polynomial Vector Field With No Polynomial Lyapunov Function arXiv:2607.16171
Unverified 2026

Sparse Root-of-Unity Isometric Mixer

Replace a dense channel-mixing matrix by a sparse complex generalised weighing matrix W with exactly w nonzero entries in every row and column, then use U=W divided by square root of w as a norm-preserving mixer. Restricting to k=2 gives a real matrix with entries in {+1,-1}; k=4 supports signed phase rotations. The exact isometry should preserve signal and gradient norms while reducing channel-mixing cost.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Complex generalised weighing matrices in centraliser algebras of monomial representations arXiv:2607.16069
Unverified 2026

Laplace-Margin Regularized Depression RNN

Augment a recurrent or state-space layer with a bounded synaptic-depression variable that multiplicatively reduces recurrent transmission after activity. During training, estimate the layer's impulse-response transform and penalize characteristic roots approaching the unstable half-plane. This directly targets slow oscillations and exploding recurrent feedback rather than relying only on gradient clipping.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: On large networks of integrate-and-fire neurons with short-term synaptic plasticity arXiv:2607.16017
Unverified 2026

Scale-Slack Homology Consistency

Regularize a neural embedding so that two augmented views of the same point cloud or graph induce homologous cycles whenever their embedded vertices move by at most δ. Instead of requiring identical topology at exactly the same distance threshold, compare homology at ε for one view with homology at ε+δ for the other, matching the paper's mathematically justified scale slack. This should discourage brittle holes and connected-component changes caused purely by augmentation noise while…

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Skeletal Homology arXiv:2607.16009
Unverified 2026

Minkowski gradient barrier for neural fields

Add a Born–Infeld/Minkowski-gradient barrier to a coordinate MLP so that its spatial gradient remains below a prescribed speed limit, rather than using an ordinary quadratic smoothness penalty. Couple the barrier with a forcing or task loss; under strong forcing, the resulting field should preferentially approach a distance-to-boundary-like profile while avoiding exploding derivatives and oscillatory solutions.

Useful6/10
Difficulty4/10
Novelty5/10
Paper: Positive and nodal solutions for the Minkowski mean curvature equation: multiplicity and asymptotics arXiv:2607.15956
Unverified 2026

Barrier-Ultrametric Trust Regions

Construct a barrier metric between neural-network checkpoints or low-loss states using transition rates on a sparse neighbor graph, and use its induced single-linkage hierarchy to restrict updates within the current basin before permitting cross-basin moves. In the large barrier-spread regime, the metric is controlled by the largest barrier along the best path, producing an ultrametric hierarchy that can replace unreliable Euclidean distance for trust-region and replay decisions.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Ultrametric organization of energy landscapes on random Erdős--Rényi graphs: topological origin of barrier hierarchy arXiv:2607.15902
Unverified 2026

Martingale Reference-Kernel Regularizer

Constrain a conditional stochastic neural module to define an approximate martingale kernel while minimizing its expected conditional Wasserstein distance to a reference law q. The module should change the input distribution only as much as necessary to match the target marginal, rather than freely reshaping every conditional distribution.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Existence of $q$-Bass martingales in the semidiscrete setting arXiv:2607.15872
Unverified 2026

Singular-perturbation continuation schedule

Use the paper's fast-layer/reduced-problem decomposition as a training schedule: first optimize a cheap reduced neural dynamics on the critical manifold, then gradually restore the fast dynamics by increasing the stiffness parameter. This provides a continuation path from an easy slow problem to the intended recurrent or implicit model and supplies a concrete stopping criterion based on normal-hyperbolicity loss.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Constructing far-from-equilibrium patterns in a cross-diffusion vegetation-autotoxicity model arXiv:2607.15692
Unverified 2026

Fold-aware fast-slow neural state layer

Replace a single recurrent or neural-ODE state update by a fast subsystem for the rapidly relaxing state and a slow subsystem for context, memory, or parameters. Constrain the learned algebraic critical manifold to remain normally hyperbolic during ordinary operation, while treating its folds as explicit, detectable transition surfaces that can generate controlled regime changes rather than numerical blow-up.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Constructing far-from-equilibrium patterns in a cross-diffusion vegetation-autotoxicity model arXiv:2607.15692
Unverified 2026

Sensitivity-aware diffusion noise schedules

Choose the diffusion noise schedule to maximize the minimum DSM sensitivity to important distribution parameters, such as mixture weights. This should reduce mode amplification and improve recovery of rare modes without changing the score-network architecture.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Diffusion models recover accurate mixture weights despite score function insensitivity arXiv:2607.15485
Unverified 2026

Perron-Weighted Cluster Consensus Optimizer

Partition parallel neural-network replicas, experts, or parameter blocks into clusters and communicate their parameters through a directed nonnegative weight matrix whose dominant eigenvector is constant within each cluster. The optimizer contracts within-cluster disagreement while retaining separate cluster-level parameter states, providing controlled specialization instead of destructive global averaging.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: A Distributed Cluster Economic Dispatch Scheme for Cross-regional Microgrids Induced by Well-designed Communication Weights arXiv:2607.15322
Unverified 2026

Pivot-separation barrier for polynomial neurons

Add a width- and degree-aware regularizer that prevents hidden polynomial neurons from collapsing to the same pivot. The paper's critical-point analysis says that non-global local minima and nontrivial saddles for cubic activation occur only when all pivots coincide, while global representations require at least d distinct active and visible pivots; the barrier directly targets this degeneracy.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Landscape analysis for shallow neural networks: Complete classification of critical points for cubic activation and affine target functions arXiv:2607.15173
Unverified 2026

Vandermonde polynomial initialization

Initialize a univariate polynomial-activation hidden layer to realize a prescribed polynomial exactly, rather than relying on gradient descent to learn the required cancellation between shifted monomials. This provides an analytically controlled starting point for polynomial MLPs, polynomial feature extractors, and teacher-to-student initialization when the desired local map is known or fitted from data.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: Landscape analysis for shallow neural networks: Complete classification of critical points for cubic activation and affine target functions arXiv:2607.15173
Unverified 2026

Divergence-Free Transport Noise Layer

Inject Stratonovich transport noise into intermediate spatial feature maps instead of adding independent elementwise Gaussian noise. Choose divergence-free vector fields whose covariance is approximately isotropic, so the corresponding Itô correction acts like a tunable Laplacian and preferentially suppresses unstable high-frequency feature components.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Absence of blow-up in the 3D Navier-Stokes equations with transport noise arXiv:2607.15140
Unverified 2026

Augmented-Lagrangian Evolution for Constrained Neural Policies

Replace a hand-tuned reward penalty in black-box policy optimization with the paper's clipped augmented Lagrangian, using separate adaptive multipliers and penalty coefficients for safety, robustness, and performance constraints. This is especially suitable for neural policies optimized with evolutionary strategies when simulator gradients are unavailable or unreliable.

Useful6/10
Difficulty4/10
Novelty4/10
Paper: SMC-ES: Automated synthesis of formally verified control policies arXiv:2607.15003