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 dense attention over structured object tokens with attention over role-filler tensor-product representations. A learned query specifies both a role and a filler, retrieves objects matching that binding, extracts a target role, and rebinds the extracted filler into an output object.
Train a neural barrier function that certifies a lower bound on the probability of reaching a target before entering an unsafe set, uniformly over an entire compact set of initial states. Add boundary and expected-drift penalties to a learned world model or policy, and enforce a positive slack margin rather than fitting only pointwise trajectories. The mechanism should improve safety under distribution shift because the certificate constrains one-step stochastic transitions throughout the…
Train a neural dynamical surrogate not only to reproduce measured trajectories, but also to reproduce the plant's economically optimal decision and objective value. Add a differentiable decision loss obtained by solving the surrogate's inner optimization problem, and reject models that fit observations while producing extra local optima or a shifted optimum.
Wrap a learned neural controller or world-model policy with a quadratic-program projection that enforces a robust higher-order control barrier condition. The projection uses a neural estimate of hidden state variables and a certified bound on model and estimator residuals, so the nominal policy is changed only when it approaches a learned safety boundary.
Train a neural policy through a differentiable dynamics model while enforcing a Control Barrier Function condition at every rollout state, rather than applying a penalty only to observed constraint violations. The barrier residual becomes a local certificate that the learned policy points inward at the boundary of the safe set, allowing safety to be checked on unseen states when combined with a margin and Lipschitz bound.
Constrain a neural policy or recurrent dynamics model to be order-preserving, then construct upper and lower abstract transitions by evaluating monotone maps at opposite corners of each state-action cell. Train with a loss that rewards the upper abstraction for reaching safe target cells and the lower abstraction for avoiding unsafe cells, while reporting the undecided gap as a quantitative certificate.
Use discovered infinitesimal generators to create small continuous transformations of hidden states and force a neural predictor to commute with those transformations. This converts symmetry discovery into self-supervised augmentation without prespecifying a group, canonical coordinates, or hand-designed equivariant layers.
Attach a quadratic-program safety filter to a neural policy that outputs a desired reference rather than directly replacing the underlying stabilizing controller. The filter uses a model of the complete closed-loop dynamics to make the smallest reference modification satisfying a control-barrier inequality, allowing aggressive neural behavior while preventing violations of state constraints.
Discretize the hidden state of an RNN, state-space model, or neural world model into cells and estimate a transition interval for every source-cell/action/target-cell triple from trajectory data. Use robust Bellman recursion on the resulting interval MDP to penalize actions or parameter updates whose worst-case probability of reaching an unsafe cell exceeds a prescribed threshold.
Replace noisy pointwise derivative matching in a neural state-space model with a weak-form Koopman-generator residual. An encoder maps observations to latent observables, while a learned matrix generator propagates those observables. Integration by parts removes the need to differentiate noisy trajectories and provides a controllable noise-averaging mechanism.
Replace pointwise spectral-norm contraction in a recurrent or state-space model with an average logarithmic contraction certificate for an input-conditioned fibre update. Let a base state carry expressive, possibly noncontractive dynamics, while an auxiliary latent fibre contracts on average. This should preserve useful variability in the base while preventing long-horizon fibre explosion and making the fibre converge to an input-dependent invariant section.
Equip a learned dynamics model with an adaptive parameter estimate and an explicit component-wise uncertainty box. Require a nominal backup-policy rollout to remain inside a safety margin equal to the rollout's worst-case parameter sensitivity, producing a conservative filter for reinforcement learning and world-model planning that becomes less conservative as the model identifies its parameters.
Augment a neural state-space model or neural ODE with a low-dimensional control residual that keeps its hidden state inside a sequence of time-varying convex sets encoding temporal requirements. At each integration step, solve a small quadratic program that minimally changes the network dynamics while enforcing an inward-pointing condition on every active convex-set face, producing robustly constrained long-horizon rollouts.
Replace a single value critic with graph-indexed critics V_alpha and graph-indexed policy heads pi_A, where the labeled graph covers every possible environment mode at every step. Train sampled Bellman inequalities rather than only equality-based temporal-difference errors, and select the policy head using the paper's min-max reachability rule. This targets robust RL settings in which the transition mode can change arbitrarily, such as unknown actuator regimes, domain randomization modes, or…
Use a neural network to predict only constitutive exchange coefficients, while a fixed skew-symmetric operator generates the conservative part of the update and a structured thermodynamic operator generates the irreversible source. The resulting layer preserves a chosen energy exactly in continuous time and can enforce nonnegative entropy production through a constrained parameterization of exchange rates.
Train a recurrent neural network or state-space model using a Poincare-style event loss: identify two consecutive latent alignment events and require the latent position and velocity at the second event to equal a transformed version of the first. Evaluate the Jacobian of this return map and penalize unstable non-neutral Floquet multipliers, producing long-horizon trajectories that are both periodic or symmetry-periodic and locally stable.
Use explicitly stochastic latent dynamics to detect hidden-state changes that are invisible in the observed output spectrum. Near the integral-memory regime, constrain or monitor cross diffusion with a forward-versus-reverse path statistic, preventing output-equivalent latent models from developing physically implausible irreversible dynamics.
Use the random-attractor construction as a training and inference diagnostic: initialize latent trajectories far in the past with different states but the same recent noise sequence, then measure whether they contract toward the same current set. This detects whether a stochastic recurrent model has a bounded, reproducible random attractor or instead exhibits discretization-induced divergence and spurious long-term modes.
Replace a dense Koopman autoencoder latent with a sparse code whose active-coordinate support can represent the local dynamical regime or basin. Train reconstruction, latent linear prediction, and multi-step rollout losses jointly; use the learned support as a label-free regime variable and optionally select a local transition matrix for forecasting.
Attach a robust, horizon-dependent uncertainty tube to a recurrent neural state-space model or learned policy. Instead of training only the nominal rollout, propagate state-estimation, model, and disturbance uncertainty through local Jacobians and impose a loss that keeps the tube inside task constraints. The method should be especially useful when short-horizon predictions are accurate but small Jacobian gains cause long-horizon divergence.
Treat the optimized surrogate and the training trajectory as objects that require a decision-level audit. Use multistart optimization to count phantom optima, and periodically evaluate whether stochastic training has changed the surrogate optimum even when validation prediction error remains nearly constant; stop, roll back, or average checkpoints when decision drift exceeds a threshold.
Train a neural controller or learned dynamics model against a finite-horizon set-valued certificate rather than only sampled trajectories. Represent uncertain states and bounded disturbances with hybrid zonotopes, propagate them through affine dynamics and a piecewise-linear neural network, and penalize reachable-set violations and failure to contract into a terminal set. This turns rare worst-case failures into a directly optimized geometric objective.
Build a recurrent or implicit neural layer from a bipartite graph containing variable nodes and equation or mechanism nodes, rather than a directed graph containing only variables. The forward pass solves all mechanism residuals simultaneously, while an intervention replaces one selected equation and fixes its target variable; this distinguishes interventions that impose the same value through different mechanisms. The resulting module is suitable for equilibrium world models, differentiable…
Replace a single smooth neural vector field with a finite collection of smooth subnetworks selected by learned affine hyperplanes. The architecture exposes switching geometry directly, allowing it to represent friction-like or threshold dynamics without approximating discontinuities using excessively steep activations.