Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Calibrate the two blend coefficients directly from a context trajectory rather than using gradient descent. The one-step prediction problem is a two-variable ridge regression, making per-task adaptation nearly free and suitable for zero-shot or few-shot system identification.
Replace a parameter-heavy recurrent transition, or use this as a fallback, with a two-parameter nearest-neighbor successor blend in latent space. Given a query latent state, retrieve the closest state from an in-context trajectory and combine the query, the retrieved state, and its observed successor; this gives a zero-shot dynamical forecast with almost no trainable transition parameters.
Replace a single recurrent state with two coupled one-dimensional latent chains whose relative alignment is periodically shifted during inference. Ferromagnetic coupling preserves locally coherent patterns, while controlled sliding produces a nonequilibrium friction effect that can make global magnetization substantially longer-lived than in a static noisy chain. The shift velocity acts as a measurable memory-control parameter rather than an unconstrained architectural hyperparameter.
Insert a differentiable implicit layer that maps boundary features to an interior latent field by solving a discrete sinh-Gordon equation. The paper's second-order convergence result motivates using a symmetric five-point discretization and a damped Newton solve rather than asking a neural network to learn the entire interior field directly.
Parameterize a recurrent or state-space layer by a matrix-valued Blaschke lift instead of an unconstrained transition matrix. The resulting causal filter is contractive for inputs inside the unit disk and energy-preserving on the unit circle, while its value at z=0 is a freely learned strict contraction.
Replace or augment a recurrent cell with multiple hysteresis memory branches whose states remain unchanged while the input stays within a branch-specific radius, then move toward the current input only when that radius is exceeded. The resulting cell has explicit persistence and bounded state changes, giving it an inductive bias for temporal hysteresis and reducing the need for the network to learn long-term memory behavior from scratch.
Replace an unconstrained recurrent memory with a truncated path-signature state that is updated continuously from the input control path. Feed this structured state to a learned vector field, allowing the model to represent path-dependent dynamics through iterated integrals of the entire history rather than only the latest hidden state.
Add an entropy-Lyapunov consistency term to a recurrent or state-space model whose learned dynamics are intended to reproduce a chaotic invariant distribution. The regularizer targets the equality condition h_mu(f) = sum_i max(lambda_i, 0), while a dominated-splitting diagnostic determines whether the theorem assumptions are approximately plausible instead of blindly forcing equality.
Replace the linear state transition in a small recurrent or state-space module by a circulant matrix acting on a vector over a finite field. The hidden state then has only finitely many possible values and follows an exactly periodic orbit after at most \(q^n\) states, eliminating numerical drift on modular-counting and symbolic-memory tasks. A learned real-valued encoder and decoder can surround the discrete core, while the transition itself is fixed, searched, or trained with a…
Replace or augment an RNN or state-space model hidden state with coordinates on a bounded 3-step nilpotent group. The first layer stores ordinary features, the second layer stores pairwise commutator memory, and the third layer stores nested commutators that can preserve three-time dependencies invisible to first- and second-order summaries. Layered reduction keeps the state bounded while retaining the algebraic interaction structure.
Equip multiple recurrent agents with a shared spatial or token-level trail field whose influence is a bounded function of accumulated visitation, rather than an unbounded additive memory. Use the paper's simultaneous/sequential invariance as a falsifiable design target: parallel and randomly ordered asynchronous agent updates should produce nearly identical predictions when trail occupancy is saturated, while deliberately nonsaturating controls should show order dependence. This can enable…
Split a recurrent or state-space model into a persistent slow state and a fast internal state. Every r recurrent steps, preserve the slow state but reset or contract the fast state toward a learned reference, reproducing selective restart rather than a destructive global reset. The expected benefit is suppression of long-range oscillatory and error correlations while retaining trajectory-level information.
Split a neural state into two subnetworks or two groups of latent channels and connect them through a conservative membrane flux instead of an unconstrained residual or concatenation. The flux is driven by the difference in chemical potential and uses an odd monotone exponential law, so the interface transfers information while guaranteeing nonnegative dissipation.
Add a decentralized safety layer to a multi-agent neural policy or learned world model. Each agent first predicts an action or short trajectory, then projects its proposal into a half-space defined by each neighbor's announced trajectory and a positive buffer, avoiding a centralized nonconvex collision solve. Use Jacobi or Gauss-Seidel iterations when agents mutually revise their predicted trajectories.
Distill a large or accurate latent transition model into a smaller discrete-state recurrent model while penalizing both its one-step transition mismatch and its lack of contraction. The filtering perturbation bound predicts that reducing the Dobrushin coefficient prevents errors from accumulating over long sequences, while reducing the transition discrepancy lowers the irreducible steady-state error.
Encode observations into a latent state in which each discrete action applies a separate linear Koopman transition matrix. Train the encoder and matrices from replay data, then use repeated matrix multiplication for multi-step prediction instead of recursively evaluating a nonlinear dynamics network. This is especially suitable for discrete-action model-based RL, where action-conditioned linear operators provide cheap rollouts and expose unstable action/state combinations.
Turn a recurrent or state-space memory into a constrained hereditary state: the latent state remains in a learned convex domain, and only input motion that reaches the boundary changes the plastic component. This creates a nonexpansive, rate-independent memory that should suppress unstable state growth and make the representation depend on meaningful cumulative changes rather than arbitrary update frequency.
For risk-sensitive or recursive objectives, add a separate network that predicts the conditional certainty equivalent of the next-state continuation value, rather than forcing the value network to approximate a nested nonlinear expectation directly. Train the value, policy, and certainty-equivalent heads with Bellman and first-order residuals jointly.
Use the M phase-aligned parameterizations produced by cyclic reformulation as an empirical ensemble of neural dynamics rather than selecting one phase or averaging only predictions. Their centroid supplies a nominal model, while their convex hull defines a low-dimensional uncertainty set used for robust rollout training and uncertainty-aware inference.
Add a slow latent two-state gate to a recurrent, state-space, or world-model network so that separate experts represent two qualitatively different dynamical regimes. Train the gate using the paper's two-state population and fluctuation mechanism rather than allowing an unconstrained softmax to average incompatible regimes. The model should allocate extra capacity near the gate's susceptibility peak, where regime uncertainty and forecast variance are predicted to be largest.
In a partially observed reinforcement-learning or model-based control agent, expose the state-estimator innovation to the action head through a dedicated residual feedback branch. The policy produces a nominal action from the estimated latent state, while a learned innovation-compensation branch corrects actions when observations disagree with predicted latent dynamics. This explicitly separates nominal policy behavior from estimation-induced corrections and should help during fast transients…
Use the same residual signal to move a neural policy's action away from a learned safety boundary when its dynamics model is unreliable. The shield evaluates a tightened constraint, so model uncertainty directly produces a larger safety margin while accurate predictions recover the original feasible set.
Represent a rare transition in a neural latent space by a controlled path whose drift is optimized directly, instead of obtaining it by reversing the relaxation dynamics. Learn a state-dependent mobility or diffusion matrix so that the sampler allocates noise and control effort according to the local stochastic geometry. This should improve generation of low-probability transitions in nonequilibrium world models and reduce the number of failed trajectories.
Retain the iteration at which each state enters each modal winning set and use that integer as a dense training target for a neural critic. The policy is additionally encouraged to choose transitions that decrease every finite modal distance, supplying progress information even when the environment reward is sparse.