Solves: Stability

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

2394 ideas found

Failed on benchmark 2026

Dynamics-Matched Contractive Reservoir

Construct a recurrent or state-space neural module whose latent dynamics are initialized from a mechanistic approximation of the target system rather than from an isotropic random matrix. For traffic-like interacting systems, use a graph reservoir with car-following-inspired relative-position and relative-velocity terms, drive it with undersensed observations, and train a linear or low-rank readout. The mechanism preserves nonlinear state encoding while enforcing an echo-state contraction…

Useful7/10
Difficulty6/10
Novelty6/10
Paper: Dynamics-matched Physical Reservoir Computing for Undersensed Traffic Prediction arXiv:2607.27371
Unverified 2026

Affine-symmetry-free GMM latent prior

Use a Gaussian-mixture latent prior whose component weights, means, and covariances admit no nontrivial affine automorphism. Add a differentiable penalty that separates component signatures, reducing permutation, reflection, and other affine ambiguities in unsupervised latent representations.

Useful7/10
Difficulty4/10
Novelty7/10
Paper: Beyond ICA: Identifiability by Symmetry Breaking arXiv:2607.23182
Mechanism failed 2026

Volume-Threshold Contracting State Layer

Construct a recurrent or state-space layer as a skew product: an expanding bounded feature coordinate drives a linearly contracting hidden state. Constrain the hidden transition matrix A to have spectral radius below one, and monitor the predicted transition ell times the absolute determinant of A equals one: below it, hidden trajectories should occupy a thin or fractal set, while above it they should have substantially higher-dimensional state coverage without losing local contraction.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Geometric Properties of Higher Dimensional Solenoidal Attractors arXiv:2607.27089
Mechanism failed 2026

Heavy-Tail Path-Adaptive Optimizer Pool

Replace one fixed optimizer time scale with a geometric pool of restarted AdaGrad trajectories, and adaptively combine them online. Short-window experts react quickly when the fine-tuning optimum moves, while long-window experts average noisy gradients; the meta-controller shifts weight between them without requiring a known noise scale, path length, or horizon.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: Parameter-Free Dynamic Regret for Online Convex Optimization under Heavy-Tailed Noise arXiv:2607.27073
Mechanism confirmed, baseline not beaten 2026

Finite-Horizon Lyapunov Risk Monitor

Treat the hidden-state evolution of an RNN or state-space model as a randomly perturbed map and estimate the distribution of finite-time expansion rates rather than only the spectral radius of an average Jacobian. Penalize high-probability positive FTLEs, allowing the model to remain expressive while controlling rare finite-horizon explosions.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Finite-Time Chaos Diagnostics and Noise-Induced Basin Merging in a Two-Dimensional Map arXiv:2607.26963
Mechanism confirmed, baseline not beaten 2026

Icosahedral Congruence-Robust Strain Sensor

Replace an unconstrained local strain encoder with six directional quadratic channels associated with the six axes of a regular icosahedron. Transform the axes by the local volume-preserving deformation gradient and reconstruct the symmetric strain tensor by a differentiable least-squares frame inverse. This preserves exact identifiability under any invertible deformation while providing a structured, rotation-balanced sensing frame.

Useful7/10
Difficulty4/10
Novelty7/10
Paper: Exact Lagrangian Realization and Robust Strain Sensing in Incompressible Flow arXiv:2607.26895
Failed on benchmark 2026

Firmly Nonexpansive Convex-Gradient Denoiser

Replace an unconstrained image denoiser or refinement block by a gradient step on an input-convex neural potential. The resulting map has a verifiable nonexpansiveness guarantee when the potential is convex and its gradient is sufficiently smooth, reducing error amplification across repeated applications and making the module safer under distribution shift.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: A Relaxed Gradient Step Denoiser for Splitting Methods in Poisson Inverse Problems arXiv:2607.26864
Mechanism confirmed, baseline not beaten 2026

Spectrally identifiable phaseless recurrent layer

Build a complex-valued recurrent or graph-neural layer whose hidden state evolves under a fixed graph Schrödinger operator and is exposed to the downstream network only through coordinate magnitudes at several times. Choose the diagonal potential so that the spectrum has unique unordered pair sums, the squared-eigenvector matrix is invertible, and every eigenvector pair overlaps in at least one observed coordinate; the resulting temporal intensity code is theoretically injective up to one…

Useful7/10
Difficulty6/10
Novelty8/10
Paper: Dynamical phase retrieval for Schr{ö}dinger evolution on finite graphs arXiv:2607.26705
Mechanism confirmed, baseline not beaten 2026

Non-Gaussian Perron–Frobenius Latent Filter

Replace Gaussian covariance propagation in a neural state-space model with a finite Perron–Frobenius operator acting on coefficients of a learned density basis. A neural encoder maps observations to latent states, while an eDMD-derived matrix transports the full coefficient vector and supports multimodal or skewed uncertainty. This creates a cheap deterministic uncertainty layer that can be rolled forward for long horizons without repeatedly sampling particles.

Useful7/10
Difficulty6/10
Novelty6/10
Paper: An extended Perron-Frobenius operator filter for nonlinear state estimation arXiv:2607.26632
Mechanism failed 2026

Sphere-Jacobian Performative Optimizer

Augment the ordinary gradient of a neural-network loss with the chain-rule term caused by the model changing the future data distribution. Estimate the unknown distribution-response Jacobian using paired rollouts at randomly perturbed parameters, averaged over a sphere-direction minibatch; this makes the method applicable when the environment is a black box and only samples from the induced distribution are observable.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction arXiv:2607.26562
Failed on benchmark 2026

Reachable-Set Risk Head for Early-Warning Rollouts

Attach a probabilistic reachable-set head to a neural world model so that long-horizon predictions produce both a mean trajectory and an uncertainty envelope. Train or calibrate the model using the probability that the predicted envelope intersects an unsafe region, allowing early-warning losses to penalize risk before an actual violation appears. The transferable signature is a predictable monotone increase in warning probability as the reachable set approaches or intersects a forbidden set.

Useful7/10
Difficulty6/10
Novelty5/10
Paper: Online Monitoring and Risk Assessment of Non-Cooperative UAVs via STL-Aware Adaptive Fusion Kalman Filtering arXiv:2607.26527
Mechanism confirmed, baseline not beaten 2026

Polar-Backstepping Policy Residual

Represent car-like navigation states in the paper's polar coordinates and make a neural policy predict only a residual around an analytic backstepping controller. Add a Lyapunov-decrease penalty so the learned residual can improve trajectory quality without destroying the nominal parking attractor.

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Global Exponential Stabilization of the Kinematic Bicycle Model of a Car in Polar Coordinates arXiv:2607.26442
Mechanism failed 2026

Active Resolvent Regularization

Replace an unconstrained recurrent or state-space transition Jacobian by a passive Gram-like component plus a controlled non-reciprocal perturbation, and regularize the resulting resolvent norm. The goal is not merely to reduce eigenvalue magnitude: it is to suppress soft and highly non-normal modes whose transient amplification can destabilize long-horizon inference even when all eigenvalues appear stable.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Non-Hermitian Random Matrix Theory of Jamming in Active Disordered Media arXiv:2607.26406
Unverified 2026

Tensorized concentration mixing

Replace a dense mixing or attention matrix on tokens arranged on a Cartesian grid by a product of learned or fixed one-dimensional concentration operators. The layer applies one axis operator at a time, reducing parameter and compute cost while enforcing that the global operator is a positive contraction with controlled spectral leakage.

Useful7/10
Difficulty5/10
Novelty5/10
Paper: Tensor factorization and explicit spectral bounds for product-box concentration operators arXiv:2607.26361
✓✓ Beats tuned baseline 2026

Conjugate Bayesian Latent Dynamics Head

Replace the final nonlinear transition network of a latent world model with a linear Koopman-style transition whose coefficients have a Matrix Normal-Inverse Wishart prior. Meta-learn the prior across tasks, then adapt only closed-form sufficient statistics from a few recent transitions; this should be more data-efficient and uncertainty-aware than gradient fine-tuning under distribution shift.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts arXiv:2607.26345
Mechanism confirmed, baseline not beaten 2026

Expansion-balanced MoE routing

Treat token-to-expert assignments as a bipartite routing graph and penalize patterns that leave token groups sharing too few experts. Enforcing sublinear expansion makes routing diversity explicit: even a moderately sized group of tokens must reach many distinct experts, reducing expert collapse and improving load balance without requiring every token to use every expert.

Useful7/10
Difficulty4/10
Novelty6/10
Paper: Recent progress in graph theory using expansion arXiv:2607.26049
Failed on benchmark 2026

Two-Column Non-Markovian Memory Core

Replace a Markovian recurrent update with an MPS-valued temporal influence state that couples adjacent pairs of memory sites, mimicking the paper's CDU3 two-column construction. The hidden state retains structured correlations across multiple past time steps while computation remains linear in sequence length and polynomial in the bond dimension, rather than exponential in the memory horizon.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Solvable Quantum Circuits with non-Markovian Influence Matrices arXiv:2607.25969
Mechanism failed 2026

State-Range Observer Gain Scheduler

Make the observation-injection gain state dependent, increasing it only when the projected unobserved dynamics approach the Hurwitz boundary. This creates a feedback controller for latent drift while avoiding the observation-noise amplification caused by using a globally oversized gain.

Useful7/10
Difficulty7/10
Novelty7/10
Paper: Data Assimilation for Chemical Reaction Networks and Population Models via a Tunable Observer arXiv:2607.25879
Mechanism confirmed, baseline not beaten 2026

Coupled multilevel gradients for Markov-stream training

Replace a conventional minibatch gradient computed from consecutive correlated samples with a coupled multilevel estimator whose fine-minus-coarse differences are evaluated on the same trajectory segment. Clip each correction and the final estimator to a certified or empirically estimated norm bound. The estimator should be most useful in streaming reinforcement learning and time-series training, where independent minibatches cannot be obtained cheaply.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization arXiv:2607.25785
Mechanism confirmed, baseline not beaten 2026

FDT-Calibrated Rotational Optimizer

Add a controlled antisymmetric component to the local parameter update so optimization can circulate around ill-conditioned valleys instead of moving only along gradient directions. The symmetric component supplies dissipation, while the skew component produces the oscillatory non-reciprocal response predicted by the paper. Adapt the skew strength only while the estimated discrete-time dynamics remain stable.

Useful7/10
Difficulty6/10
Novelty7/10
Paper: Fluctuation-dissipation violations in mean-field non-reciprocal spin glasses arXiv:2607.25782
✓✓ Beats tuned baseline 2026

Joint latent-actuator identification

Add a low-dimensional actuator-distortion model alongside a neural state-transition model instead of assuming that commanded control is the realized control. For a transition $x_{t+1}=F_\theta(x_t,u_t^{\mathrm{cmd}}+d_\phi(x_t,u_t^{\mathrm{cmd}}))$, jointly fit the intrinsic dynamics parameters $\theta$ and disturbance parameters $\phi$, with a strong simplicity prior on $d_\phi$. This should prevent the dynamics network from absorbing systematic actuator errors and improve cross-regime…

Useful7/10
Difficulty5/10
Novelty7/10
Paper: Joint identification of permanent magnet synchronous machine and inverter arXiv:2607.25739
Mechanism confirmed, baseline not beaten 2026

Stieltjes Event-Driven Neural State Layer

Replace a uniformly stepped recurrent or state-space transition with propagation measured in an effective clock that may pause on intervals and make finite jumps at events. Use an implicit Stieltjes-Euler residual for every interval and event, then differentiate that exact residual with a reverse discrete adjoint. This should provide stable long inactive periods, exact scheduled resets, and fewer computational steps than approximating instantaneous events with many tiny chronological-time steps.

Useful7/10
Difficulty6/10
Novelty6/10
Paper: Exact discrete-adjoint optimization of trap timing and placement in a Stieltjes-time reaction-diffusion model: A Galicia case study arXiv:2607.25450
Failed on benchmark 2026

Critical-Slowing-Down Safety Monitor

Attach a model-free critical-slowing-down monitor to hidden states, actions, residuals, or losses generated by a recurrent neural controller or state-space model. When the monitored dynamics show increasing variance and lag-one autocorrelation, reduce the controller gain or optimizer learning rate, increase damping, shorten the rollout horizon, or switch to a fallback policy before the neural system reaches an unstable regime.

Useful7/10
Difficulty4/10
Novelty7/10
Paper: Critical slowing down for predicting controller induced loss of control in quadrotors arXiv:2607.25370
Mechanism confirmed, baseline not beaten 2026

Residual-screened Koopman latent bottleneck

Add a small linear latent transition to a neural encoder-decoder and use normalized Koopman eigenfunction residuals to identify unreliable latent modes. Rather than retaining every eigenmode of the learned transition, reconstruct forecasts only from modes whose one-step residual is small on held-out temporal windows. This turns spectral decomposition into an explicit denoising and model-selection mechanism for neural state-space models.

Useful7/10
Difficulty5/10
Novelty6/10
Paper: On residual bounds of the EDMD solution to the eigenvalue problem for the Koopman operator and backward shadowing stability of the EDMD/KMD arXiv:2607.25086