Research ideas

Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.

2030 ideas found

Unverified 2026

Finite-domain survival-time MoE router

Replace a static top-k MoE capacity rule with a router whose expert allocation evolves through a finite-domain coverage process. Experts with larger current occupancy can either receive more future capacity, intentionally amplifying specialization, or receive less capacity by reversing the size dependence, allowing a controlled test of the paper's asymmetry-amplification mechanism.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Size-Dependent Growth Rates Amplify Infinitesimal Asymmetry in Nanocrystals arXiv:2609.00145
Unverified 2026

Zero-mode MPS front-end for constrained sequence models

Build a constrained autoregressive model whose initial logits are generated from a translation-invariant MPS associated with a local zero-mode construction. The MPS supplies a structured valid distribution before a Transformer residual is added, so the model starts on the constraint manifold instead of learning validity through a penalty.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Efficient search for excitable zero-modes in constrained systems arXiv:2608.31165
Unverified 2026

Anisotropic mass-force regularizer for neural surfaces

Add a Michael-Simon-inspired penalty to a neural implicit surface, neural renderer, or differentiable mesh generator. The penalty suppresses large-area sheets whose anisotropic first variation is small, which should reduce spurious folds, floating components, and geometrically unstable solutions while preserving surfaces required by the task loss.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: The anisotropic Michael-Simon inequality arXiv:2608.31164
Unverified 2026

Principal-bundle gauge-fixed Hamiltonian network

Represent a time-dependent Hamiltonian system on the reduced state $(q,t,p_q)$ rather than on the redundant extended state $(q,t,p_q,p_t)$. A neural Hamiltonian section predicts one canonical representative of each affine cotangent fiber, while an optional symmetry loss enforces consistency under transformations that translate time.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Reduction of symmetric time-dependent Hamiltonian systems I: presymplectic principal $\mathbb{R}$-bundles arXiv:2608.28278
Unverified 2026

Level-Set Balanced Sparse Mixer

Partition activations into dyadic magnitude bands and allocate sparse connectivity separately to heavy and diffuse coordinates. Protect high-magnitude coordinates with more reliable connections while using randomized flat connectivity for the many small coordinates, keeping the total number of nonzeros fixed.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Level-set entropy and sparse randomized embeddings arXiv:2607.23017
Unverified 2026

Fake-Stationary Volterra Memory Layer

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.

Useful5/10
Difficulty6/10
Novelty5/10
Paper: On (fake) Stationarity in Stochastic Volterra Equations with Affine Drift and Regular Kernels arXiv:2608.31099
Unverified 2026

Weak-Bounded Riesz Attention

Replace one local spatial aggregation in a CNN or vision transformer with a discretized Riesz potential whose kernel is proportional to $\|x-y\|^{-(n-s)}$. Normalize the layer using the paper's sharp weak-type constant and penalize empirical violations of the resulting tail bound, encouraging nonlocal context without allowing a small set of pixels or tokens to generate arbitrarily large responses.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Sharp constants for weak estimates of Riesz Potentials when $0<s<\min\{n,2\}$ arXiv:2608.31043
Unverified 2026

Caveman-calibrated resolution schedule

Use the paper's analytic merging threshold to choose the Scaled-NAP exponent from an intended community size rather than treating alpha as an arbitrary hyperparameter. A warm-started schedule can begin with persistence-like fine structure and increase alpha only when the model has learned reliable local groups.

Useful5/10
Difficulty3/10
Novelty8/10
Paper: Scaled Null-Adjusted Persistence: A Multiscale Bridge between Modularity and Persistence arXiv:2608.30934
Unverified 2026

Certified Rank-Aware QP Layer

Use a Goldfarb–Idnani-style active-set solver as a neural constrained layer or optimizer substep, but never trust a guessed active set solely because its linear system solved. Remove duplicate or dependent constraints, solve the reduced KKT system, and accept the result only after checking primal feasibility, dual sign conditions, and stationarity. This gives exact enforcement of linear inequalities and a diagnostic certificate when the constraint set is infeasible.

Useful5/10
Difficulty6/10
Novelty5/10
Paper: Goldfarb-Idnani Revisited:Invariants, Certificates, and the Limits of Guessing arXiv:2608.30933
Unverified 2026

Minkowski-Symmetry Activation Ellipsoid

Replace ordinary per-coordinate activation normalization or covariance whitening with a learned or frozen affine map based on a minimum-volume ellipsoid calibrated to the activation convex hull. Estimate the hull's Minkowski symmetry and use the bound \(\rho=\sqrt{d/\alpha}\) to set a principled clipping radius, where \(d\) is feature dimension and \(\alpha\) is the measured symmetry. This should reduce worst-case clipping of asymmetric activation distributions without requiring a much larger…

Useful5/10
Difficulty6/10
Novelty4/10
Paper: Symmetry-dependence in Rounding of a Convex Body arXiv:2608.30876
Unverified 2026

Flux-Frequency Homogeneity Regularizer

Add a differentiable penalty that encourages a neural implicit field to have a controlled local homogeneity degree across concentric spatial scales. The penalty compares the flux-normalized frequency at adjacent radii, optionally targeting a desired degree k, so the network is discouraged from producing scale-inconsistent or oscillatory local geometry.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: An Almgren-type formula for planar $p$-harmonic functions arXiv:2608.30847
Unverified 2026

Dominance-Fold Graph Pooling

Before message passing, repeatedly detect a pair of vertices with nested open neighborhoods and fold away the dominated vertex while preserving its information in the surviving vertex's feature state. The graph reduction is justified by homotopy invariance of the independence complex, while the feature merge prevents task-relevant attributes from being lost. Add a topology-aware ablation comparing this exact fold against random node pooling and standard learned pooling.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: The Homotopy Types of the Independence and Perfect Matching Complex of Möbius Ladder Graph arXiv:2608.30601
Unverified 2026

Cross-Channel Vector Wavelet Front End

Replace a channelwise wavelet or strided-convolution front end with vector-valued wavelet filters that deliberately pair different scalar wavelets across channels. The resulting subbands retain compact-support multiscale structure and can be recombined exactly, while a small learned 1x1 mixing layer operates on the cross-channel coefficients instead of learning a full expensive convolution at every scale.

Useful5/10
Difficulty5/10
Novelty4/10
Paper: Vector-Valued Wavelet Bases as Hilbert $\mathbb{M}_m(\mathbb{R})$-Module Bases: A Construction from Scalar Wavelets arXiv:2608.30589
Unverified 2026

Central-Path ReLU Inequality Layer

Replace a hard nonnegative slack or ReLU output by the barrier-derived map \(x_s(w)=\frac{w+\sqrt{w^2+4s}}{2}\). Unlike an arbitrary smooth activation, this output is the unique positive solution of \(x(x-w)=s\), so the network can explicitly monitor complementarity and anneal \(s\) toward the true inequality-constrained solution. Use it in a constrained output head or in hidden layers whose activations represent nonnegative resource, probability, or routing slack variables.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: A Barrier-Regularized Symmetric Nitsche Method for the Signorini Problem arXiv:2608.30470
Unverified 2026

Krasikov-Normalized Jacobi Feature Layer

Replace raw polynomial features in a scalar MLP expansion with endpoint-weighted orthonormal Jacobi features. The paper's envelope gives a degree- and parameter-aware scale for each feature, preventing high-degree terms or endpoint behavior from dominating gradients while preserving a richer approximation basis than low-degree monomials.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: The Erdélyi--Magnus--Nevai and Krasikov Conjectures for Jacobi Polynomials arXiv:2608.30304
Unverified 2026

Indefinite Grassmann Adapter

Replace an unconstrained low-rank adapter or similarity projection with a learned subspace carrying a prescribed signed metric. The module learns an orthonormal basis U for a k=p+q dimensional subspace, forces the compressed form U^*I_{m,n}U to have p positive and q negative eigenvalues, and uses the resulting pseudo-inner product for signed attention or retrieval scores.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: The Grassmannian of indefinite subspaces arXiv:2608.30249
Unverified 2026

Covariance-aware Gaussian clipping calibration

Use the Gaussian approximation of a high-dimensional maximum to set a simultaneous coordinate-clipping threshold for minibatch gradients or activations. The threshold is sampled from a correlated Gaussian with the observed batch covariance, rather than treating coordinates as independent or estimating an unstable extreme quantile directly.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Cubic-Root Gaussian Approximation under Unrestricted Covariance arXiv:2608.30221
Unverified 2026

Heisenberg Bracket Positional Encoding

Replace or augment standard sinusoidal or RoPE position features with bracket-quadratic phases $e(-\theta n\lfloor\beta n\rfloor)$ generated by a Heisenberg nilmanifold orbit. Multiple irrational coefficients and output frequencies produce a cheap deterministic encoding whose empirical cross-position correlations should exhibit cancellation instead of the periodic aliasing of rational or finite-frequency encodings.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Sets whose differences avoid a bracket quadratic arXiv:2608.30078
Unverified 2026

Singularity-Aware Groupoid Transport Layer

Replace a globally shared latent transformation group by a source-dependent collection of valid transformation paths. A feature at latent point z is transported only along paths whose transformed coordinate never reaches the singular locus, while homotopic paths are identified and composable paths are concatenated. This should let an equivariant model represent branched or incomplete symmetries that ordinary group-equivariant layers must discard.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Lie groupoid integration of singular isometries of the Poincaré disk arXiv:2608.30077
Unverified 2026

Convex-hull difficulty curriculum

Interpret the Cramér energy of an embedding as the logarithm of the number of random in-distribution samples required to reach it through a convex hull. Use this quantity to stratify training data into geometric difficulty levels and schedule exposure from low-energy central points toward high-energy boundary points, or preferentially replay high-energy points after the model has learned the core distribution.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Cramér transform, half-space depth and threshold phenomena for convex bodies arXiv:2608.29972
Unverified 2026

Quadratic Gaussianization for Sign Layers

Add coefficient-spreading and moment-calibration mechanisms to binary or sign-noised linear layers. For each output neuron, normalize its real-valued weights and penalize large normalized coordinates, so its signed preactivation obeys the paper's quadratic Gaussian approximation rather than the weaker linear bound. This should make activation scales more predictable and reduce training instability caused by highly concentrated binary projections.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: A Sharp Small-Coefficient Variant of Khintchine's Inequality and the Sharp $π/2$ Theorem arXiv:2608.29703
Unverified 2026

Convex-Order Distributional Distillation

Represent each neural prediction as a finite probability distribution and project it, under an optimal-transport cost, onto the set of distributions dominated by a teacher or target distribution in convex order. This enforces a global spread and risk relationship across all convex observables rather than adding separate variance, tail, and calibration penalties. Use a periodically refreshed projection during training and test whether it improves uncertainty calibration and robustness at equal…

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Central limit theorem for Wasserstein projection - the case of convex order arXiv:2608.29565
Unverified 2026

Quadratic-Hessian cone regularizer

For a coordinate-based neural network u_theta(x) solving a fully nonlinear second-order PDE, replace the raw quadratic-Hessian residual with the concave, homogeneous operator G(D_x^2 u_theta)=sqrt(sigma_2(D_x^2 u_theta)). Add differentiable barriers that keep the predicted Hessian inside the positive branch Gamma_2, preventing optimization from entering regions where the PDE operator is non-elliptic.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Interior $C^{2,α}$ Regularity for the Quadratic Hessian Equation arXiv:2608.29484
Unverified 2026

Review-Period Phase Diagram for Frozen Updates

Treat the number K of minibatches between expensive control updates as a review period: the controlled neural dynamics use parameters or decisions computed at time nK and hold them fixed until (n+1)K. Scan K, estimate first and second finite differences of validation loss or episodic return, and use the resulting nonmonotone-to-convex or concave phase diagram to select an update frequency rather than assuming that more frequent updates are always better.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Review-Period Sensitivity in Multiclass Queue Scheduling arXiv:2608.29398