Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Replace real diagonal state-space channels with complex damped oscillators whose hidden states encode both amplitude and phase. Train with parallel causal convolution and deploy with the equivalent one-step recurrence, allowing the same layer to support efficient batched training and low-memory streaming inference.
Replace a learned dense token-mixing matrix or residual-state transition with a sparse diffusive mixer whose Laplacian has a deliberately small largest Jordan block. Balance the two chain lengths around the central coupling/core, because the paper proves that this minimizes the worst defective transient among the tridiagonal family. Use a scalar residual step size to move the non-consensus spectrum inside the unit disk while preserving the sparse structure.
Add a small constrained equilibrium layer whose response depends on the current neural state and recent exogenous history, then cache responses keyed by a learned history embedding. For a new history, reuse a cached response only when an empirical Wasserstein distance to the cached history is below a threshold; otherwise run a few inner optimization iterations. The paper's local Holder and trajectory-stability results motivate graceful degradation rather than catastrophic errors for nearby…
Replace independent Gaussian attention noise or unconstrained token routing with a directed-polymer path distribution over positions and layers. The router aggregates exponentially many monotone paths through temporally correlated random edge scores, producing heavy-tailed but spatially coherent routing and preventing attention from collapsing onto a single token. The paper's t^{2/3} wandering and t^{1/3} free-energy fluctuations become measurable diagnostics and tunable targets rather than…
Represent periodic input-output behavior using a compact real vector of Fourier coefficients and learn an invertible neural map from input coefficients to output coefficients. Inference then obtains the input representation for a desired periodic output by a single inverse pass instead of iterative optimization through a nonlinear forward model, while the Fourier representation reduces sequence dimensionality when high-rate signals are spectrally sparse.
Add a state-dependent damping term to a continuous-depth residual block, but constrain damping over trajectories rather than forcing every layer to be contractive. A trajectory receives damping only when it enters a designated high-risk region of activation space; a finite-window penalty requires each sampled trajectory to accumulate at least a target amount of damping, preserving expressivity while suppressing exploding hidden states and unstable numerical dynamics.
Replace eigenvalue-only stability checks for a continuous-time recurrent or state-space layer with an explicit finite-horizon transient-growth test. Penalize state matrices that have small spectral decay but large induced norms of exp(tA), exp(tA^{-1}), or their discretized transition operators. This targets the paper's phenomenon in which a system is exponentially stable in continuous time yet numerically and inversely unstable because its eigenbasis is highly conditional.
Use the paper's density-regularity criterion to regularize a neural conditional transition model or Koopman operator. Penalize the Sobolev energy of the learned conditional density or conditional feature embedding with respect to the conditioning state, then constrain the induced operator's Hilbert–Schmidt norm or singular-value tail. The goal is a verifiable finite-rank approximation guarantee for stochastic rollouts, not merely a generic smoothness prior.
Add a causal memory branch whose weights are generated by the paper's power-type Volterra kernel rather than learned independently at every lag. Learn or softly constrain the exponents so the model can select rough short-memory behavior or smoother long-memory behavior while using only a few parameters. The branch can be implemented as a truncated causal convolution, a multiresolution approximation, or a recurrent state-space realization.
Replace repeated full-dimensional matrix-exponential or ODE solves in a conditioned continuous-time state-space layer with contour quadrature evaluated in a projection basis. The same reduced basis and contour nodes can serve many conditioning vectors, while shifted reduced resolvents provide a stable and differentiable approximation over a prescribed time window.
Construct a recurrent module with a phase variable and a transverse memory coordinate modeled on a perturbed twist map. Train the transverse state to lie on an invariant graph over the phase, while the phase follows an approximately irrational rigid rotation. A KAM-inspired graph correction and residual penalty should reduce long-horizon drift in recurrent prediction.
When a learned operator changes during training, add a frame-connection correction that transports its current Arnoldi representation instead of allowing hidden states to jump between evolving spectral directions. This is a geometry-aware residual or optimizer correction intended to reduce representation drift during aggressive learning-rate schedules, fine-tuning, and continual learning.
For local structures with a forward/reverse ambiguity, expose both ordered directions and add one explicit orientation bit. This creates a shared bidirectional positional encoder that can distinguish reflected neighborhoods without maintaining two completely independent directional encoders.
Replace a time-invariant linear state-space transition with a periodic transition whose coefficients have a learned period T. Constrain the product of one period to be contractive, and regularize its Fourier sidebands so that periodically driven modes do not accumulate unstable resonant energy. The architecture predicts an observable stability boundary through the spectral radius of its monodromy matrix and a measurable sideband occupation profile.
Constrain the numerical range of a learned recurrent or state-space transition matrix instead of constraining only its eigenvalues or singular norm. The resulting Crouzeix certificate controls every polynomial time filter, including multi-step powers and residual propagation, and is designed to suppress transient amplification caused by nonnormality.
Replace expensive global spectral analysis of a sparse graph propagation matrix, banded SSM transition matrix, or linearized layer with smallest-singular-value calculations on overlapping local sections. Penalize local sections whose pseudospectrum enters a forbidden region, adding the paper's explicit C0/L safety margin so that the resulting constraint has a principled finite-window error tolerance.
Construct a 2D recurrent or residual neural lattice with slowly varying local couplings, while parameterizing those couplings so that an anisotropy invariant remains constant across all spatial and depth locations. The network obtains controlled local propagation velocities rather than arbitrary inhomogeneous amplification, enabling depth-dependent receptive fields while preserving near-critical signal propagation.
Replace a delayed optimizer state or gradient by a causal lower-triangular history transformation that predicts the current descent direction from recently stored states and inputs. Use Fredholm terms to incorporate the recent history and Volterra terms to preserve causal invertibility, then apply the optimizer update in transformed coordinates. This targets oscillation and divergence caused by concurrent delays in distributed or asynchronous training.
Use the paper's Margulis-type law as a structural constraint for neural continuous-time dynamics: the number of isolated periodic latent trajectories with period at most T should grow like exp(hT)/T in a positive-entropy regime. This provides a falsifiable test for orbit collapse, excessive chaos, or spurious recurrence in neural ODE world models, rather than relying only on one-step prediction loss.
Estimate persistent frequencies in a neural-network training trajectory using a smooth weighted Birkhoff average instead of a rectangular moving average. Use the estimated frequency vector to detect low-order resonances between optimizer oscillations, gradient-noise cycles, and validation-loss oscillations, then trigger a learning-rate or momentum intervention before divergence.
Equip a recurrent or state-space layer with multiple noncommuting transition operators and regularize the span of finite operator words applied to the input injection matrix. This discourages hidden directions that cannot be reached from the input and may improve long-range input influence, gradient propagation, and robustness under operator switching.
Insert a constraint-aware observer between a neural state-space transition and its next prediction. The observer propagates latent event times, incorporates partial observations, and projects the result onto the set satisfying both lower-bound causality and upper-bound token-lifetime constraints, preventing impossible latent trajectories from entering the recurrent model.
Replace an unconstrained recurrent or residual transition with a block-structured contractive realization whose input-dependent multiplier is a direct sum of bounded branches. The resulting layer has a built-in non-expansive energy bound on the chosen normalized input domain, while still allowing different branches to respond to different coordinates or feature groups.
Replace a learned nonnegative banded transition matrix by an ordered product of learnable stochastic bidiagonal factors. Each factor performs one local left or right transport step, so a product of p lower and q upper factors creates an effective bandwidth of p+q while retaining nonnegative entries, row sums equal to one, and a highly structured propagation kernel.