Solves: Stability

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

2414 ideas found

Unverified 2026

One-Step Saddle Deviation Regularizer

Add an action-level exploitability penalty to alternating training of two neural policies that play against each other. For each observed state, estimate the value of forcing every available action against the opponent's current policy, then penalize positive gaps from the player's minimax value rather than relying only on the sampled action or episode return. This should expose locally exploitable decisions earlier and reduce oscillation between adversarial policies.

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Baseball, An Extensive-Form Game-Theoretic Duel arXiv:2607.29041
Unverified 2026

Oja Gradient-Subspace Optimizer

Track the dominant rank-r subspace of the gradient covariance online, then use that basis to construct a low-rank adaptive update or a controlled preconditioner. Unlike offline PCA refreshes, the Oja flow continuously follows changing training geometry while preserving orthonormality, potentially reducing the cost of second-order or Shampoo-like methods.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: On the Oja-Flow-Based Low-Rank Approximation of Kalman-Bucy Filters for Linear Time-Varying Systems arXiv:2607.29034
Unverified 2026

Cycle-Invariant Loss for Gauge-Free Matrix Prediction

Train a neural network that predicts a symmetric matrix family without choosing a particular latent basis. In addition to matching pointwise eigenvalues, match gauge-invariant relational quantities formed by traces of products of matrices at several inputs; these distinguish matrix families that have identical spectra at every input but differ in their shared eigenvector geometry. Evaluate the result after one global orthogonal Procrustes alignment, not by independently aligning every sample.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Stable Recovery of Matrix Gauge Classes from Pointwise Invariants arXiv:2607.29021
Unverified 2026

Delay-Robust Cooperative Recurrent Cell

Build a recurrent cell that uses a filtered predecessor state and explicitly accounts for stale communicated features, following the paper's delay-augmented state-space construction. The cell is trained under variable activation delays and constrained so that local closed-loop dynamics remain stable, targeting robustness of long-horizon rollout rather than only one-step prediction.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: A Cooperative Implementation of Mesh Stability in Vehicular Platoons arXiv:2607.28953
Unverified 2026

Null-form quadratic wave layer

Replace an unconstrained quadratic interaction between channel derivatives with a learnable combination of Lorentzian and antisymmetric null forms. For wave-equation surrogates, this enforces exact cancellation when two interacting features have parallel null directions, suppressing resonant derivative products that otherwise cause unstable long-horizon rollouts.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Recovery of a Null Form in the Wave Equation from Scattering Data arXiv:2607.28917
Unverified 2026

Interacting Hypothesis-Bank Optimizer

Replace one potentially misinitialized training trajectory with K parallel parameter hypotheses, each representing a different basin or latent explanation, and combine them using loss-derived mode probabilities. Before each update, mix the hypotheses through a transition matrix so that a temporarily poor or incorrect mode can inherit information from a promising mode while retaining multimodal diversity. This is most appropriate for nonconvex networks, latent-variable models, or long-horizon…

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Adaptive Attitude Estimation for Multiple-Surface Object Using Light Curve Glints arXiv:2607.28912
Unverified 2026

Geometric parallel optimizer portfolio

Run several independent copies of an optimizer with geometrically increasing training budgets so that at least one copy is close to the unknown budget required by the problem. Allocate workers using staggered schedules rather than launching a full hyperparameter sweep, and periodically select or promote the best checkpoint using a held-out minibatch stream. This targets training regimes where the required number of updates is unknown because smoothness, gradient variance, or noise level is…

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Adaptivity via a Parallel Architecture for Stochastic Gradient Methods arXiv:2607.28902
Unverified 2026

Demographic Synchronizing Expert Layer

Replace static mixture-of-experts routing weights with positive expert abundances that undergo phase-dependent birth, death, and crowding. Each expert has an internal phase and natural frequency; experts aligned with the population order parameter receive larger effective abundance, while a logarithmic penalty prevents runaway replication. The mechanism creates a measurable synchronization transition and can serve as a differentiable alternative to hard top-k routing.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Synchrony by Birth and Death arXiv:2607.28867
Unverified 2026

Localized Spectral Redistribution

Add a selective redistribution branch to recurrent or graph propagation layers whose local Jacobian gains are too large. Instead of globally shrinking the layer, blend the unstable update at only the offending coordinates with a volume-weighted average of those coordinates and their upstream neighbors, using the paper's explicit threshold as the minimum stabilizing blend.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Spectral Analysis and Redistribution Thresholds for Cut-Cell Finite-Volume Methods arXiv:2607.28808
Unverified 2026

Dual-Gibbs Gaussian latent layer

Replace slow primal-coordinate Gibbs sampling of a graph-structured Gaussian latent feature field with Gibbs sampling in the Fourier-dual factor graph. Use the primal convergence formula to determine when dual sampling is worthwhile, and map dual samples back to neural features through the graph incidence operator.

Useful6/10
Difficulty7/10
Novelty7/10
Paper: Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs arXiv:2607.28706
Unverified 2026

Stochastic Bilevel Structure Learning

Replace a hard, separately precomputed graph partition or expert assignment with partition-inducing parameters sampled from a learnable Gaussian distribution. Train the neural representation in an inner loop and update the distribution parameters using an outer validation loss, allowing the discovered structure and predictor to co-adapt while retaining gradients through otherwise discrete assignments.

Useful6/10
Difficulty6/10
Novelty5/10
Paper: MPP-GNN: Subject-Adaptive Community Detection for fMRI-Based Alzheimer's Disease Classification arXiv:2607.28681
Unverified 2026

Geometrically Random Transport Network

Construct a deep sequence model as a layered channel network with fixed random K-regular connections between neighboring depth layers, instead of dense or independently random weight matrices. Use norm-preserving edge normalization and a reversible residual update so that geometric randomness controls information transport while trainable nonlinear readouts provide task-specific computation. The architecture exposes a tunable crossover between quasi-one-dimensional ballistic or localized…

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Quantum Chaos and Diffusive Transport from Geometric Randomness arXiv:2607.28579
Unverified 2026

Normalized Scheduling-Degree Truncation

Use normalized scheduling variables and explicitly cap the degree of their products in a neural LPV or mixture-of-dynamics model. Instead of allowing every multiplicative interaction between scheduling coordinates and past or future features, retain only monomials below a chosen degree threshold. This produces a controllable approximation knob between a purely linear model and a full lifted predictor, while avoiding unstable extrapolation caused by poorly scaled high-degree features.

Useful6/10
Difficulty5/10
Novelty5/10
Paper: A subspace approach to data-driven predictive control for linear parameter-varying systems arXiv:2607.28490
Unverified 2026

Parabolic Torus Recurrent Core

Construct a recurrent state-space model with a neutral quasiperiodic phase variable and transverse amplitude variables whose non-autonomous coupling decays polynomially in inference time. The phase subsystem provides persistent torus-like memory, while the transverse subsystem receives only a vanishing perturbation, limiting long-horizon drift caused by continual corrections.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Non-autonomous KAM theory for lower dimensional invariant tori (II): Normally parabolic case arXiv:2607.28472
Unverified 2026

Distance-Powered Boundary Ansatz for Fractional PINNs

Represent the predicted solution as $u_{\theta}(x)={\rm d}_{\Omega}(x)^s v_{\theta}(x)$, where $v_{\theta}$ is an unconstrained neural network and ${\rm d}_{\Omega}$ is the distance to the boundary. This builds the fractional Dirichlet boundary layer into the architecture and leaves the network to learn the smoother quotient $u/{\rm d}_{\Omega}^{s}$, which the paper proves extends Hölder-continuously to the boundary when the reaction has sufficient integrability.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: On boundary regularity for the fractional p-Laplacian with unbounded reactions arXiv:2607.28436
Unverified 2026

Windowed Bouncy Particle Weight Sampler

Replace stepwise gradient evaluation in a Bouncy Particle sampler over neural-network parameters with deterministic windows. At the start of each window, compute one gradient and use smoothness to upper-bound the event intensity along the ballistic trajectory; candidate events are generated analytically from the integrated envelope and accepted using a gradient evaluation only at candidate locations. This gives an exact sampler under a certified global smoothness bound and a controllable…

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Windowed thinning and query complexity for the bouncy particle and Zigzag samplers arXiv:2607.28413
Unverified 2026

Caret-Invariant Tree-Pair Mixer

Represent a token sequence or image region partition by a pair of planar rooted binary trees and a permutation of their leaves, following the tree-pair model of Thompson-type groups. Train the mixer to produce the same output whether a leaf is left intact or refined into two child leaves that are immediately merged by a matching inverse refinement. This creates a variable-resolution hierarchical module with an explicit consistency constraint instead of relying on an arbitrary fixed tree depth.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Thompson's Group $V$ and Virtual Link Theory arXiv:2607.28406
Unverified 2026

Tangential probability-flow sampler

Modify the probability-flow ODE of a reflected diffusion so that its learned velocity is tangent to the constraint boundary. Use an exact tangent projection for box or sphere constraints, or a smooth boundary-collar correction for general domains, and train with an additional penalty on the predicted normal flux. This prevents numerical trajectories from leaving the domain and targets the no-flux structure directly instead of clipping samples after each solver step.

Useful6/10
Difficulty4/10
Novelty5/10
Paper: Reflected diffusion, no-flux continuity equations and confined Lagrangian flows in bounded domains arXiv:2607.28344
Unverified 2026

Coherence-to-Diffusion Graph Layer

Replace a single graph or token-mixing operator with two coupled channels: an antisymmetric, coherence-preserving transport channel and a state-dependent dissipative diffusion channel. The local feature state controls the dissipative edge rates, so strongly occupied or conflicting regions are smoothed while weakly interacting regions retain rapid coherent propagation.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Interacting Quantum Symmetric Exclusion Process arXiv:2607.28255
Unverified 2026

Directional Almost-Dominance OT Loss

Add a directional optimal-transport penalty that discourages samples from a model distribution P from exceeding samples from a reference distribution Q in task-relevant coordinates, while allowing a calibrated amount of violation controlled by γ. Unlike symmetric Wasserstein matching, the loss distinguishes harmful upward or downward deviations and can encode that one predictive or reward distribution should dominate another.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Almost stochastic dominance via optimal transport arXiv:2607.28215
Unverified 2026

Sheaf Compatibility Robustness Loss

Attach vector-valued local features to simplices, nodes, edges, or hyperedges and penalize violations of sheaf restriction maps that should make local predictions agree on shared higher-order structures. Evaluate the compatibility loss on progressively degraded subcomplexes, producing a persistence-style robustness objective that rewards features whose global consistency survives structural failures.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Interval Decompositions for Multipersistence Modules over Finite Posets and Robustness of Sheaf Data on Simplicial Complexes arXiv:2607.28134
Unverified 2026

Cutoff-Free ECT Perimeter Feature

Compute a translation- and rotation-robust perimeter feature from the Euler Characteristic Transform and append it to learned shape features. Unlike a finite-radius ECT comparison, the point-anchor subtraction cancels the constant Euler-characteristic tail exactly, eliminating the need to tune a spatial cutoff.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: The Euler Characteristic Transform from a Convex Geometric Perspective arXiv:2607.28021
Unverified 2026

Mpemba Spectral Restart

Use the slow-mode content of a neural network's local optimization dynamics to choose between a near restart and a deliberately larger restart concentrated in fast-curvature directions. The larger perturbation is predicted to recover faster when it has substantially smaller overlap with the slowest Hessian modes, producing an explicit Mpemba crossover in loss or validation recovery.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Mpemba effect in a chemomechanical model of the Kinesin molecular motor arXiv:2607.27998
Unverified 2026

Layered Structural Reachability for Neural States

Treat the hidden-state Jacobian of an RNN, SSM, or graph neural network as a directed matrix-weighted network and decompose repeated block couplings into scalar interaction layers. Use layer-specific structural controllability to select input, skip, reset, or readout channels that can reach all hidden dimensions, and reject architectures with structurally unreachable states before training.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: On the Strong Structural Controllability of Matrix-Weighted Networks arXiv:2607.27852