ML: Rnn

Machine-learning ideas tagged Rnn in the ML taxonomy of the Math2NN corpus.

583 ideas found

Unverified 2026

Data-Identified Neural Dependency Graph

Partition a neural state or feature vector into blocks and identify directed dependencies between blocks from one-step transition data. Use the inferred design structure matrix as a hard mask or soft gate on recurrent, state-space, graph, or mixture-of-experts couplings, replacing a dense unconstrained interaction matrix with a data-supported sparse graph.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Novel methodology for obtaining design structure matrices using network identification arXiv:2608.16759
Unverified 2026

Order-Sensitivity Margin Regularizer

Train a threshold-reset recurrent network to suppress dependence on unresolved excitatory/inhibitory arrival order. Penalize states that fall in the paper's order-sensitive firing interval, or augment training with excitatory-first and inhibitory-first counterfactuals and enforce consistent outputs.

Useful6/10
Difficulty4/10
Novelty8/10
Paper: Order-Sensitive Fast-Synapse Limits in Sparse Excitatory-Inhibitory Threshold-Reset Networks arXiv:2608.16701
Unverified 2026

Folded-Gaussian Soft-Mode State Space

Initialize a stable diagonal state-space layer with decay rates \(\omega_i=|\xi_i|\), where \(\xi_i\sim\mathcal N(\mu,\sigma^2)\), instead of using a narrowly clustered rate distribution. The nonzero density of rates near zero creates a population of slow modes whose aggregate impulse response has an algebraic tail, enabling long-horizon memory while every finite-dimensional mode remains exponentially stable.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Statistical Mechanics of a Quantum Harmonic Oscillator with Folded Gaussian Frequency arXiv:2608.16617
Unverified 2026

Subcritical Gradient-Cascade Control

Treat a small activation, gradient, or parameter perturbation as a seed and measure the number of newly affected downstream units or layers. Use the estimated branching ratio to control the optimizer step size or residual gains, keeping training in a subcritical regime where perturbation cascades have finite expected size instead of amplifying through the whole network.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Absence of critical scaling in the Schelling segregation model arXiv:2608.16557
Unverified 2026

Polynomial-Mixing Block Training

Use the paper's separated-block construction to train recurrent or state-space networks on trajectories with slowly decaying temporal correlations, rather than treating consecutive frames as independent minibatch samples. Thresholded events such as collision, failure, saturation, constraint violation, or reward exceedance are aggregated over blocks with empirically chosen gaps and optionally replaced by finite-resolution cylinder approximations. The method predicts a measurable power-law…

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Statistical properties for irregular observables in slowly mixing hyperbolic systems arXiv:2608.15569
Unverified 2026

Jensen-Gap Regularization for Temporal Cascades

Add a mean-preserving periodic-input consistency penalty to a stacked leaky recurrent or state-space network. The penalty suppresses output shifts caused purely by hidden-state fluctuations and nonlinear curvature, improving invariance to temporal modulation while preserving the average input signal.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: Gain of Entrainment in Nonlinear Cascades arXiv:2608.15214
Unverified 2026

Near-Parseval Unitary Orbit Memory

Generate memory slots or attention keys by applying learned unitary transformations to one seed vector instead of storing every slot independently. Select transformations sequentially when they add a sufficiently new direction and reject phase-equivalent or highly coherent candidates, targeting a well-conditioned near-Parseval frame.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Near-Parseval orbit frames for irreducible unitary representations: from mixing and expansion arXiv:2608.15182
Unverified 2026

Differentially Positive Recurrent Core

Constrain the Jacobian of a recurrent or state-space transition to preserve a prescribed cone of admissible hidden-state perturbations. This imports differential positivity into neural dynamics and makes long-run hidden trajectories order-preserving rather than allowing arbitrary sign-changing perturbation growth.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Birkhoff center and recurrent behavior of differentially positive systems on a homogeneous space arXiv:2608.14980
Unverified 2026

Laguerre Memory Convolution

Replace the length-L learned convolution kernel in a causal sequence layer with K Laguerre basis functions, where K is much smaller than L and the basis parameter controls the decay time scale. The layer retains a long receptive field but learns only K coefficients, while FFT or a fixed state-space realization evaluates the resulting convolution efficiently. This is especially appropriate for audio, sensor streams, and long-context regression where the desired impulse response is smooth or…

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Impulse Response Estimation via Laguerre-Fourier Expansion arXiv:2608.14769
Unverified 2026

Continuous Ergodic Projection for Recurrent States

Given a learned recurrent dynamics map, estimate a state-dependent invariant measure from each trajectory and use integration against that measure as a projection onto long-term invariant features. Penalize discontinuities of this projection between nearby states and assign zero mass to trajectories whose feature norms escape, producing a principled distinction between convergent attractors and divergent rollouts.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Continuous pointwise ergodicity for semigroup actions on locally compact spaces arXiv:2608.14175
Unverified 2026

Non-Abelian KPZ State-Space Coupling

Augment a sequence model with a scalar phase-like latent field and several coupled channel fields, then add a KPZ-style nonlinear gradient drift between neighboring sequence positions. The coupling is made dimension-aware: it can remain active in effectively one- or two-dimensional latent dynamics, but is annealed toward zero in higher-dimensional dynamics where the paper predicts that weak nonequilibrium perturbations become irrelevant.

Useful6/10
Difficulty7/10
Novelty8/10
Paper: Far-from-equilibrium scaling of non-abelian Goldstone modes arXiv:2608.13666
Unverified 2026

Vortex-Criticality Controller for Phase RNNs

Represent recurrent hidden states as compact phases and monitor spacetime vortices, defined by wrapped phase differences around elementary space-time plaquettes. Add a feedback controller that increases relaxation toward the homogeneous phase when vortex activity becomes supercritical, while allowing larger recurrent gain when the system is excessively quiescent. This creates a falsifiable operating regime: useful computation should occur near, but below, the defect-proliferation transition…

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Far-from-equilibrium topological phase transition in one dimension arXiv:2608.13658
Unverified 2026

Midpoint Consistent-Gain Cancellation

Augment a recurrent or diagonal state-space neural block with online interval estimates for persistent transition gains. At every step, intersect the current parameter interval with the set compatible with the latest transition and bounded residual, then use its midpoint for certainty-equivalent cancellation. The method learns passively and avoids the transient spikes caused by exploratory probing or endpoint selection.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty arXiv:2608.13651
Unverified 2026

Learned Busemann Stable Leaves

Learn an endpoint-conditioned scalar potential whose level sets represent states with the same asymptotic behavior, analogous to the paper's stable magnetic orthospheres. Train the dynamics to contract differences within a level set while preserving differences between distinct endpoint classes, producing a latent representation organized by stable manifolds rather than Euclidean proximity.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Surfaces with nonpositive magnetic curvature arXiv:2608.13534
Unverified 2026

Surrogate-guided topology search for nonlinear reservoirs

Search sparse reservoir wiring in graph space rather than repeatedly testing every candidate with its full nonlinear dynamics. Use graph descriptors to predict validation accuracy and nonlinear feature selectivity, then spend exact simulations on candidates with high predicted performance or high surrogate uncertainty.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Graph-theoretic design of lasing networks for physical vision arXiv:2608.13097
Unverified 2026

Rank-One SRB Latent Dynamics

Replace an unconstrained recurrent latent transition with a map having one deliberately expanding angular coordinate and strongly contracting transverse coordinates. The construction should produce a bounded chaotic attractor with a reproducible stationary distribution while preventing uncontrolled expansion in the remaining hidden dimensions.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: The Bosch and Simó conjecture on the Shilnikov-Hopf bifurcation arXiv:2608.13021
Unverified 2026

Hyperbolic State Transition Regularization

Constrain a recurrent or state-space transition matrix so that its eigenvalues avoid a configurable annulus around the unit circle. This creates a stable/unstable decomposition and should reduce the accumulation of numerical, quantization, and activation-update errors over long sequences while preserving controlled long-term memory.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Topological shadowing for linear operators arXiv:2608.12862
Unverified 2026

Empirical-Covariance-Weighted Low-Rank Dynamics

Apply the paper's weighted nuclear elastic-net principle to the transition matrix of a recurrent or linear state-space layer. Penalize low-rank structure after whitening by the observed hidden-state covariance, while retaining a ridge term that prevents poorly excited state directions from producing unstable or arbitrarily large transition weights.

Useful6/10
Difficulty6/10
Novelty5/10
Paper: Weighted Nuclear Elastic Net Estimation of (Near-) Low-Rank Drift Matrices in Ornstein-Uhlenbeck Processes arXiv:2608.12838
Unverified 2026

Intermittent Multi-Mode Memory Gate

Add a bounded routing state to an RNN, state-space model, or mixture-of-experts layer, with several neutral fixed points representing persistent modes. The state moves between modes when far from a fixed point but escapes each mode only polynomially when close to it, creating controllable long memory without setting a linear eigenvalue arbitrarily close to one. A temperature parameter selects between an entropy-rich phase using many modes and a low-entropy phase concentrated near one preferred…

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Thermodynamic formalism for intermittent maps with multiple neutral fixed points and phase transitions arXiv:2608.12784
Unverified 2026

Near-Return Entropy Monitor for Recurrent Latent Dynamics

Use the paper's separated near-return criterion as a finite-data certificate that a recurrent or latent dynamical model contains positive-complexity behavior rather than merely noisy prediction error. Detect pairs of nearby trajectories that almost return to their starting points but separate at an intermediate time, then either flag the model for long-horizon unreliability or penalize the number and strength of such events. The monitor is suited to learned world models, RNNs, and neural ODEs…

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Shadowing in the presence of singularities: oriented versus standard shadowing, entropy and the structure of recurrent sets arXiv:2608.12165
Unverified 2026

Projective Spectral Anti-Flattening

Insert a projective normalization and spectral monitor into a recurrent or deep residual dynamical block. If the effective linearized map has one real eigenvalue whose modulus dominates all others, the block is predicted to collapse features toward one direction; constrain the spectral ratio or preserve a controlled two-dimensional rotational mode to maintain representational rank.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Area-Normalized Pentagram Map Dynamics: Spectral Flattening and Elliptic Asymptotics arXiv:2608.11781
Unverified 2026

Resonance-Aware Momentum Damping

Apply a Birkhoff-normal-form-inspired monitor to momentum optimization and recurrent-state updates, where oscillatory modes are identified from recent parameter or hidden-state trajectories. When two dominant frequencies approach a low-order ratio such as 2:1 or 3:1, increase damping before nonlinear mode coupling produces large oscillations; away from resonance, retain the faster low-damping update.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Nonlinear Stability, Resonances, and Singular Reduction in the Unequal-Mass Equilateral Restricted Four-Body Problem arXiv:2608.11494
Unverified 2026

Void-Singularity Noise Scheduler

Use the conditioning of a learned symmetry-commutant manifold as a training-time detector for frozen or weakly reachable hidden-state regions. When replica observables become nearly linearly dependent, the commutant Gram matrix becomes ill-conditioned; reduce injected noise and learning rate there, or perturb only directions with measurable response. The mechanism predicts a transition in relaxation curves at a conditioning threshold rather than relying only on validation loss.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Geometry of Noisy Quantum Many-Body Dynamics with Continuous Symmetries: Entanglement and Correlations arXiv:2608.11297
Unverified 2026

LP-Synthesized Bounded Residual State

Replace an unconstrained recurrent residual update with a sparse coordinated state-space block whose gains and state radii are synthesized jointly by a linear program. The block receives bounded feature disturbances, keeps every hidden coordinate inside a certified interval for all time, and uses an affine feedforward correction to reduce the output sensitivity of downstream coordinates.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Certificate-based Synthesis of Coordinated Droop Control for Heterogeneous Radial Distribution Networks arXiv:2608.11141