Solves: Stability

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

2414 ideas found

Unverified 2026

Stealthy Low-Frequency Activation Regularizer

Treat active spatial sites or routed tokens as an empirical point process and penalize their Fourier power in a chosen neighborhood of zero frequency. Unlike ordinary total-variation or decorrelation penalties, this specifically suppresses large-scale count fluctuations while allowing fine-scale structure to remain, potentially stabilizing sparse routing and convolutional feature maps.

Useful5/10
Difficulty3/10
Novelty6/10
Paper: Stealthy point processes and lattice induction arXiv:2607.25616
Unverified 2026

Brjuno Resonance Curriculum

Train Fourier or state-space neural models by eliminating well-conditioned spectral modes first and retaining near-resonant modes until a later stage. The schedule is determined by the small-divisor geometry of a reference transport vector, with a cumulative Brjuno-like budget controlling how aggressively spectral corrections may be applied. This should prevent rare nearly resonant modes from producing disproportionately large gradients or unstable long-horizon rollouts.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Brjuno condition through best approximations and the linearization problem arXiv:2607.25610
Unverified 2026

Reduced-Green discrepancy regularizer

Regularize a set of learned neural representations by the Green-kernel energy of their signed discrepancy from a target background distribution. Unlike a standard pairwise repulsion term, the regularizer penalizes both over-concentration and under-coverage relative to the prescribed density, and an indefinite kernel can encode attractive as well as repulsive interactions.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: An indefinite Coulomb interaction from the Steklov spectrum of perforated manifolds arXiv:2607.25211
Unverified 2026

Fast Feedback-Constrained Optimizer

Replace penalty-based equality-constrained training with a two-timescale optimizer. A fast variable tracks the normal correction that drives constraint residuals toward zero, while the slow parameter update follows the task gradient projected onto the local constraint tangent space. This should reduce sensitivity to very large penalty weights and preserve feasibility more accurately during training.

Useful5/10
Difficulty5/10
Novelty5/10
Paper: Distributed Nonlinear Equality-Constrained Optimization via Feedback Linearization and Singular Perturbation arXiv:2607.25193
Unverified 2026

Dyadic Expert-Overload Barrier

Replace or augment the usual MoE load-balancing loss with a multiscale convex hinge penalty on expert token loads. The penalty is nearly linear for normal loads and increases superlinearly only after successive capacity thresholds are crossed, targeting the long tail of overloaded experts without strongly perturbing balanced routing.

Useful5/10
Difficulty3/10
Novelty5/10
Paper: No Gelation and Global Existence for a Boltzmann Equation with Regularly Varying Mass-Exchange Rates arXiv:2607.25112
Unverified 2026

Green-Trace Cycle Regularizer

Use the resolvent trace as a differentiable statistic that controls how strongly a learned routing or recurrent transition matrix returns to short cycles. Penalizing this quantity suppresses accidental short feedback loops, while matching a target trace can impose a desired memory profile in recurrent, graph, or mixture-of-experts architectures.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Arithmetic Landscape Functions of a Discrete Cat Map arXiv:2607.24857
Unverified 2026

Christoffel Event Scheduler

Use a Christoffel word as a periodic binary gate for an expensive training operation: activate the operation exactly r times in every N-step period, but distribute those activations as uniformly as possible rather than in blocks or independent Bernoulli trials. Candidate operations include SAM perturbation steps, Hessian-vector preconditioning, gradient clipping, EMA teacher refreshes, or an auxiliary MoE expert. The intended benefit is lower burst-induced gradient variance at the same average…

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Christoffel words as extremal structures in Collatz dynamics arXiv:2607.24844
Unverified 2026

Grazing-aware kinetic boundary loss

For a neural approximation $f_\theta(x,v)$ of a kinetic transport solution, weight boundary-condition errors by the trace measure induced by the transport field rather than sampling or penalizing all phase-boundary points uniformly. Use $\omega_p(a)=\min\{|a|,|a|^p\}$ with $a=v\cdot n(x)$; $p=1$ is the natural flux weight, while larger $p$ suppresses poorly resolved grazing interactions more aggressively and can be selected from the boundary regularity.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Sharp kinetic trace theory arXiv:2607.24708
Unverified 2026

Derangetropy Rank Warp

Insert a distribution-free rank warp before selected MLP or attention projections. For each scalar activation, replace its empirical rank u by the cumulative interval map induced by the Type-III derangetropy kernel, optionally followed by Gaussian or affine output calibration. The transform is invariant to strictly increasing reparameterizations of the feature and contracts the marginal toward central ranks, potentially reducing sensitivity to heavy tails and outliers.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Derangetropy Operators arXiv:2607.24705
Unverified 2026

Polynomial Tube Regularizer

Regularize a two-dimensional latent class support or decision-boundary projection by requiring its measured small-radius tube area to follow the quadratic law predicted for conic geometry. Penalize the fitted linear and quadratic coefficients only weakly, but strongly penalize nonquadratic residuals and rapidly changing coefficients across training checkpoints. The intended effect is to remove cusps, tangential near-contacts, and narrow gaps without directly imposing smoothness on the network…

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Conic reach and polynomial parallel volume in the plane arXiv:2607.24487
Unverified 2026

Conditional MTP2 lattice regularizer

Add a structural loss that penalizes violations of conditional MTP2 for a modelled conditional CDF. For conditioning vectors and outcome thresholds ordered componentwise, the model is encouraged to satisfy a multiplicative lattice inequality, which should produce more coherent conditional distributions and imply useful stochastic and tail monotonicity properties.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: An MTP$_2$ property for conditional distributions arXiv:2607.24394
Unverified 2026

Visible-Time Drift Training

Train a neural drift model for a partially observed diffusion using only increments accumulated at times when the latent process is visible, while feeding the projected observation as the state input. The projection may create boundary finite-variation artifacts, but the paper's visible-time identity implies that these artifacts do not bias stochastic estimating equations restricted by the visibility indicator.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Nonparametric Drift Estimation for Multidimensional Stochastic Differential Equations under Censoring arXiv:2607.24088
Unverified 2026

Phase-aware Oja preconditioner

Use Oja's streaming eigenvector estimate on a parameter block's incoming gradient stream, but activate its rank-one preconditioning correction only after the mathematically predicted d log d sample threshold. Before that point, the estimate is treated as unreliable and the optimizer remains close to AdamW or SGD. This prevents early noisy spectral directions from destabilizing training while retaining an O(d)-memory alternative to storing a full gradient covariance matrix.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: The Phase Transition in Online PCA Depends on $n/d\log(d)$, not $n/d$ arXiv:2607.23914
Unverified 2026

Sharp Curl-Helicity Regularizer

Add a scale-invariant inequality penalty to a neural vector-potential model on a discretized round 3-sphere. The penalty enforces the theorem's sharp lower bound between the L^{3/2} norm of the predicted magnetic field B=curl A and its helicity H=<B,A>, discouraging pathological high-frequency or spatially concentrated fields that fit observations but have implausible geometry. A divergence-free gauge and Killing-form initialization make the constraint numerically well-conditioned.

Useful5/10
Difficulty5/10
Novelty9/10
Paper: The sharp curl-Sobolev inequality arXiv:2607.23827
Unverified 2026

Permutation-invariant hyperedge load balancing

Replace ordinary expert-load balancing with an all-pairs discrepancy penalty for each structured expert bundle. The penalty forces every class represented in a bundle to receive similar assignment mass, avoiding dependence on an arbitrary cyclic ordering and exposing imbalances between nonadjacent classes.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Stability in stochastic hypergraph matching I: necessary and sufficient criteria arXiv:2607.23778
Unverified 2026

Sequence-Distortion Hidden-State Regularizer

Regularize the hidden-state trajectory of a sequence model so that the distance between states at positions i and j follows a controlled power-law profile in |i-j|. This explicitly prevents representation collapse over long contexts while avoiding the requirement that all distant states be maximally separated. Use alpha as a tunable geometry parameter and compare alpha against the effective hidden dimension using the paper's Euclidean realizability threshold.

Useful5/10
Difficulty3/10
Novelty6/10
Paper: Sequence distortion for metric spaces arXiv:2607.23713
Unverified 2026

Central-Moment Feature Mixer

Replace raw polynomial interactions between neighboring feature vectors with central polynomial interactions computed after subtracting the local feature mean. Keep separate second-, third-, and fourth-order channels and apply independent residual gates to them, so a uniform shift of every feature in a neighborhood cannot create artificial cross-order responses. This is a drop-in higher-order mixer for a small transformer or graph neural network.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Central-Hermite Sensing and Collision for Frame-Robust Order-Resolved Relaxation on D3Q125 arXiv:2607.23629
Unverified 2026

Effective-sample switched neural state model

Replace a single recurrent transition with K mode-specific neural transitions and train them using mode-aware normalization derived from the effective sample size T p_i. The model explicitly preserves the distinction between frequent and rare dynamical regimes, preventing frequent modes from dominating the shared training objective while avoiding unstable updates for poorly observed experts.

Useful5/10
Difficulty4/10
Novelty4/10
Paper: Learning switched non-linear dynamical systems from a single trajectory arXiv:2607.23502
Unverified 2026

Magnitude-Euler Path Signature Regularizer

Represent the computation graph of an MLP as a directed acyclic Lawvere metric space and compute a truncated, length-resolved Euler signature of its active paths. Add a penalty that separates signatures between classes while suppressing signatures that are insensitive to labels, thereby encouraging globally distinct computation routes without changing layer widths or degree statistics.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Magnitude homology and Euler characteristics of directed acyclic graphs arXiv:2607.23357
Unverified 2026

Sharp thin-shell representation regularizer

Add a radial-fluctuation penalty to a feature layer after explicitly centering and whitening its activations across the minibatch. The paper supplies an interpretable threshold, eight times the feature dimension, for the variance of squared feature norms. The penalty activates only when empirical radial variance exceeds that threshold, avoiding unnecessary pressure toward constant-norm representations.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Digesting the proof of the sharp thin-shell inequality arXiv:2607.23307
Unverified 2026

Grunbaum Entropy-Preserving Router

Replace arbitrary learned thresholds in a binary MoE or hierarchical latent router with a threshold at the batch mean of a learned scalar projection. Add a penalty when the entropy of either routed subgroup falls too far below the parent entropy, using the paper's sharp constant as the target. This discourages routing branches from becoming nearly deterministic or semantically impoverished while retaining a simple, cheap gating operation.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Entropic analogues of Grünbaum's inequality arXiv:2607.23269
Unverified 2026

Residual-Contraction log1p Kernel

Implement \(\log(1+u)\) through the bounded residual \(\rho(u)\), refining the argument by repeated square roots and propagating the residual backward with a rational recurrence. Use this table-free approximation in softplus and log-sum-exp kernels, where millions of logarithms are evaluated and predictable arithmetic can outperform general-purpose library calls on vectorized hardware.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: A Fixed-Point Construction of the Elementary Transcendental Functions arXiv:2607.23196
Unverified 2026

Factor-Two Neural Model-Criticism Test

Use a frozen neural discrepancy score and conditional Monte Carlo replicas to test whether a generative model or learned sampler is compatible with a null data distribution, without requiring mixed chains or joint exchangeability. The resulting empirical p-value has a finite-sample false-alarm bound of at most two times the nominal level, making it safer than an ordinary Monte Carlo rank test for validation and deployment monitoring.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Monte Carlo testing: non-asymptotic guarantees without joint exchangeability arXiv:2607.23010
Unverified 2026

Spectrum-preserving conditional binary graph sampler

Build a graph-structured binary latent layer whose local heat-bath probabilities are predicted by a neural network, while particle-exchange and refresh rates remain fixed. The learned probabilities change the stationary distribution and encode input-dependent conditioning, but the spectral invariance result predicts that they do not change the Markov-chain eigenvalues or relaxation modes. This provides a conditional sampler with a fixed, calibratable mixing budget instead of requiring a new…

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Mixing times and spectra of non-equilibrium symmetric exclusion processes on general graphs arXiv:2607.22991