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 a generic recurrent transition with two coupled unitary transitions that share one block column and differ by a sign on the other block column. Each transition preserves hidden-state norm exactly, while the structured difference gives a controlled two-path recurrent architecture for long-context modeling.
Replace an unconstrained latent transition by a layer with a distinguished scalar coordinate \(t\) and a symplectic leaf state \(x=(q,p)\). The layer advances \(t\) through a Reeb drift while updating \(x\) with a symplectic Hamiltonian step, preventing arbitrary mixing between progression and content coordinates and potentially improving long-horizon stability.
Add a learned Riesz-transform branch that extracts normalized spatial gradients after diffusion by a positive parabolic operator. The diffusion branch carries smooth semantic content, while the Riesz branch represents boundaries, motion changes, and graph discontinuities. Resolvent smoothing makes the derivative branch less sensitive to feature noise than directly applying a finite difference.
Add a fixed or weakly parameterized residual mixer whose interaction between sequence positions at distance \(r\) is proportional to \(1/(r\log^2 r)\). Instead of truncating the kernel at a short radius, represent its heavy tail with dyadic distance bands and compute each band using prefix sums or block pooling, giving every token access to arbitrarily distant context at roughly \(O(L\log L)\) cost.
Extract a small set of stable exponential modes from an observed neural sequence and use them to initialize a diagonal or block-diagonal state-space model. Hankel-pencil eigenvalues propose the modes, while persistence across shifts and contour margins reject modes caused by noise or a short-lived background.
Build an input-conditioned unitary transformation as an ordered product of exponentials of anti-Hermitian matrices, with each factor controlled by a univariate function of one input coordinate or one learned scalar projection. This replaces a dense multivariate matrix-valued controller with separable scalar nonlinearities while preserving exact unitarity at every forward pass.
Model the scalar feedback route in a recurrent layer as a rank-one perturbation of its open-loop transition. Regularize the frequency response of that route so that no mode reaches unit loop gain, directly targeting oscillatory and slowly decaying instabilities rather than relying only on gradient clipping.
Add a conservative correction after low-rank tensor compression so selected linear moments of an activation or learned state are exactly preserved. This can reduce tensor rank and memory without allowing compression error to accumulate in physically meaningful global quantities.
Replace a discrete or one-hot recurrent state table with a low-dimensional vector memory whose event embeddings are orthogonal whenever the corresponding events are mutually exclusive in an input exclusivity graph. The module uses continuous state vectors and can therefore target dimension \(d=\xi(G)\), whereas a discrete state encoding is lower-bounded by \(N\geq\chi(G)\). This should be tested on graph-defined formal-language recognition tasks, where the graph is known and the claimed…
Replace an unconstrained feature vector entering a rational or resolvent-like neural operator by a polynomial feature whose first nonzero Taylor coefficient lies in a pole-safe subspace. For a pole of order m, the simplest guaranteed construction is psi(z)=(z-beta)^m v, which makes Q(z)psi(z) bounded even when Q(z) diverges. For lower-order cancellation, solve linear constraints among Taylor coefficients of psi so that all negative Laurent powers vanish.
Replace a free-form order-dependent gate with a positive mixture of Mellin powers $(1+s)^{-a}$. This gives a small, interpretable module whose response across the order variable is automatically generated by a positive measure and therefore inherits complete monotonicity, log-convexity, and Hankel-moment structure.
Add a two-sided cone-restricted spectral penalty to a recurrent or state-space model. Instead of estimating growth using a symmetric singular-value surrogate, jointly optimize a positive right vector and positive left vector in the extended quotient from the paper, targeting a real generalized eigenvalue of the learned non-selfadjoint transition operator.
Parameterize a relative-position or lag-decay function as a finite positive mixture of exponentials instead of learning arbitrary attention bias values. The resulting kernel is completely monotone on positive distances, so it is nonnegative, decreasing, and has alternating derivative signs; the mixture provides several learned memory scales without allowing oscillatory or unstable long-range biases.
Augment a recurrent or state-space layer with a finite-order causal Volterra compensator that models and cancels dominant nonlinear feedback around a stable linear transition. Use quadratic terms by default and add cubic terms only when the model must operate farther from equilibrium, making truncation order an explicit compute and robustness control.
Replace pointwise spectral normalization of an RNN transition with a stability constraint on the entire family of input-conditioned matrices. Use a learned positive-definite metric P so every transition contracts in the same state geometry, approximating the paper's uniform exponential stability and input-forgetting guarantee.
Choose the retained context length by balancing the statistical complexity of adding lag j against the squared prediction bias from discarding it. Unlike a fixed context window, the rule uses both the remaining-horizon spectrum and the estimated tail energy, allowing a model to expand or shrink its memory online.
Replace a standard nonlinear recurrent transition with a truncated Carleman lift containing levels $z_j\approx u^{\otimes j}$, coupled by linear maps that represent quadratic, linear, and forcing terms. The resulting transition is linear in the lifted state but still expresses nonlinear dynamics in the original state, while the highest-order omitted interaction supplies an explicit truncation-defect signal that can be used for adaptive order selection or regularization.
Estimate the temporal spectrum of each sequence channel using a locally private procedure, then apply a regularized inverse-square-root spectral filter before the sequence enters attention or an SSM. The filter removes predictable low-frequency or narrow-band redundancy while avoiding unstable amplification at frequencies where the private estimate is small.
Replace a contractive recurrent transition by its explicit Schäffer isometric lift, optionally augmenting it with a second operator satisfying the nonlinear covariance relation $V_1V_2=V_2f(V_1)$. The lifted state preserves or nearly preserves hidden-state energy, while the covariance penalty or parameterization imposes an algebraic structure on multiple recurrent channels.
Parameterize a multi-channel two-dimensional convolutional operator through a learned filter bank B, then use the composed operator B*B as the layer response. Its Fourier response is positive semidefinite exactly at every spatial frequency, enabling stable smoothing or diffusion-like residual updates without frequency-grid penalty terms.
Add a cheap spectral gate to a state-space model or recurrent event detector that decides whether multi-step lookahead can change the threshold decision. If the learned threshold readout is approximately a nonnegative left eigenvector of the transition matrix, use the current state only; otherwise activate predictive heads and search over a small horizon. This avoids unnecessary rollout computation while preserving early-warning behavior in oscillatory or rotating dynamics.
Replace a one-step recurrent update with a causal convolution over past affine innovations using an exponential-fractional kernel. Add mean reversion and calibrate the innovation amplitude so that activation mean and variance remain approximately invariant across sequence position while retaining long-range, power-law-like memory.
Replace or augment a low-dimensional recurrent transition with affine maps whose linear parts belong to a structured unipotent holonomy family, and train the cell so that positive accumulated translation produces a controlled projective attractor. This creates a measurable two-basin long-horizon behavior: hidden-state perturbation directions should align with a learned direction X or its antipode according to the sign of a scalar functional, rather than exhibiting unconstrained rotation or…
Build a sparse recurrent graph-neural layer on a path-by-path, path-by-cycle, or cycle-by-cycle latent lattice using a skew-zero-forcing seed set and its forcing order as a causal update schedule. Only the currently forced target node is activated at each step, so a small number of anchor states can propagate through the complete lattice while retaining local connectivity and periodic-boundary structure. The exact seed-count formulas predict the minimum number of anchors required by the graph…