Math: Geometry

Machine-learning ideas tagged Geometry in the Math taxonomy of the Math2NN corpus.

646 ideas found

Unverified 2026

Second-Order Rigidity Regularizer

Add a rigidity-based regularizer to a neural graph or point-cloud encoder whose output coordinates are constrained by selected pairwise distances. The regularizer detects infinitesimal edge-length-preserving motions using the rigidity matrix, then uses equilibrium stresses to penalize deformation directions that survive at first order but are not blocked at second order. This targets representation collapse and locally ambiguous geometric embeddings.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Deformations and second-order rigidity of polytopes arXiv:2607.09252
Unverified 2026

Subduction-Based Tangent Augmentation

Train a predictor on quotient-consistent tangent jets rather than only on transformed samples. Generate several local representatives of the same orbit, compute first-order feature perturbations, and aggregate them through a shared tangent module before prediction. This gives a structured alternative to treating augmented views as independent examples and can improve robustness to composed transformations.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Diffeological Riemannian orbifolds arXiv:2607.08939
Unverified 2026

Dynamical-Degree Expansion Scheduler

Use the tropical dynamical degree as an analytic expansion budget for repeated neural blocks. Layers with $pq>4$ deliberately expand along a known tropical eigendirection, while layers with $pq\leq4$ avoid exponential asymptotic growth; a schedule can therefore increase representational mixing without allowing hidden-state norms to explode.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Complex dynamics perspective for birational maps of the plane arising from cluster algebra mutations arXiv:2607.08125
Unverified 2026

Lattice-Laplace Polytope Attention

Replace or augment conventional dot-product attention with features generated by a convex polytope's lattice Laplace partition function. For a query-dependent point inside a learnable polytope, the log-partition gradient is the expected lattice direction under a Gibbs distribution, while its Hessian is a covariance matrix that supplies curvature-aware features.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Dual Lattice Functions of Polytopes arXiv:2607.08101
Unverified 2026

Horizontal Contact Neural ODE

Replace an unconstrained latent ODE vector field with a contact-Hamiltonian flow whose velocities lie in a horizontal distribution spanned by a small set of vector fields. Couple the latent state to a scalar energy or confidence variable through a strictly decreasing value-dependent Lagrangian, giving expressive but dissipative dynamics rather than unrestricted feature drift.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Weak KAM theorems for subriemannian Lagrangians depending on the unknown function arXiv:2607.07966
Unverified 2026

Invariant cone positive feature head

Constrain selected degree-four feature blocks to represent globally nonnegative binary quartics using a positive-semidefinite Gram matrix. This gives a structured alternative to unconstrained activations for energy, uncertainty, density, or direction-dependent gating features that must remain nonnegative under every planar direction.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: On 4-dimensional convex projective domains invariant by a lattice of $\mathrm{SL}_2 (\mathbb{R})$ arXiv:2607.07150
Unverified 2026

Mapping-Cone Boundary Consistency Loss

Augment a neural model with a learned target differential form and a source-side correction whose compatibility is enforced by the mapping-cone differential. For a map F from M to N, train the model so that the target quantity is closed and its pullback to M is exactly the differential of the correction, providing a structured bulk-boundary consistency constraint instead of independent feature matching.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Periods, prequantization, and rigidity in relative multisymplectic geometry arXiv:2607.07149
Unverified 2026

Euler-Balance Regularizer for Binary Neural Fields

Add a global Euler-characteristic residual to a network predicting complementary phases A and B on a voxel grid or simplicial mesh. The regularizer forces predicted phase topology and separating-interface topology to satisfy the tubular-tiling balance law, helping reject geometrically plausible but topologically inconsistent segmentations. It is especially suitable when labels cover only one phase, interfaces are noisy, or the hidden complementary phase must be inferred.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Soft cells, Tubular Tilings and the Hidden Phases in Binary Mixtures arXiv:2607.06810
Unverified 2026

Annealed Infinity-Harmonic Dual Head

Add a two-channel geometric head producing scalar fields u(x) and v(x) on a two-dimensional input or latent coordinate domain. Train it initially with a moderate p-harmonic duality constraint, then anneal p upward so u approaches an infinity-harmonic field while v remains its rotated-gradient dual; this penalizes isolated steep gradient spikes and promotes smooth, coherent level sets.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Infinity-harmonic functions and inverse mean curvature flow clusters arXiv:2607.06698
Unverified 2026

Affine directional Sobolev regularizer

Replace the usual squared input-Jacobian penalty with a stochastic approximation of the affine Sobolev energy, which computes an inverse-power spherical average of directional derivative norms. The negative exponent emphasizes directions with unusually small sensitivity and prevents the regularizer from being represented only by the largest-gradient direction.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Stability for the Affine Sobolev Inequality and its Critical Points for $p\ge 2$ arXiv:2607.06415
Unverified 2026

Generating-Function Symplectic Layer

Replace an unconstrained recurrent transition on a state (q,p) with a discrete variational transition generated by a strictly convex distance-like function L(q,q_1). The next state is found from the implicit reflection equation L_2(q,q_1)+L_1(q_1,q_2)=0, while the induced two-form is preserved by construction; this should reduce energy-like drift and exploding or vanishing sensitivity over long sequences.

Useful5/10
Difficulty6/10
Novelty4/10
Paper: Symplectic billiards as Minkowski billiards arXiv:2607.05986
Unverified 2026

Flat Task-Transport Connection

Replace independent per-task fine-tuning directions with a learned connection that transports shared network weights across a low-dimensional task or domain coordinate space. Penalize connection curvature so that adapting from task A to task C directly agrees with adapting through intermediate task B, reducing order-dependent drift and improving interpolation between sparsely observed tasks.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Shifted Poisson unfoldings and quantum anomalies arXiv:2607.05918
Unverified 2026

Gap-Aware Hopf Stability Loss

Train a neural field to output a symmetric conformation tensor C(x) while penalizing large spatial variation whenever its leading eigenvalue approaches the second eigenvalue. The resulting loss directly targets the mechanism identified by the paper: a topological change cannot occur cheaply unless the field develops a small spectral gap or a sufficiently concentrated gradient.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Hopf Obstruction and Transported Forced Brakke Motion in Ordered Viscoelastic Cores arXiv:2607.05879
Unverified 2026

Rigidity-Calibrated Set Attention

Augment pairwise attention on a set of n tokens with a rigidity operator derived from normalized pairwise directions. The operator couples infinitesimal node displacements through changes in pairwise distances, while the complete-graph theorem provides a geometry-independent eigenvalue target n/2 after spherical centering and normalization.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: The Second Largest Eigenvalue of Stiffness Matrices of Normalized Complete Frameworks arXiv:2607.05472
Unverified 2026

Multiscale noncommutative area penalty

Use the paper's central correction as an explicit regularizer on latent trajectories. Penalizing signed-area forcing across refinement levels should prevent repeated geometric injections from creating the paper's linear growth of scaled first differences and logarithmic smoothness loss.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: A Heisenberg Subdivision Scheme with Central Smoothness Loss arXiv:2607.05446
Unverified 2026

Microscopic Boundary Pooling

Replace uniform set or point-cloud pooling with a microscopic weighting computed from pairwise feature-space distances. The resulting signed pooling vector should retain boundary and geometrically isolated points that ordinary mean pooling suppresses, potentially improving recognition when class information is concentrated on shape extremities or rare local configurations.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: The microscopic weighting on a metric space arXiv:2607.05349
Unverified 2026

Centralizer-Constrained Hyperbolic Dynamics

For data with known hyperbolic or Möbius symmetries, constrain learned infinitesimal transformations to commute with the symmetry group generators. This produces a neural ODE, recurrent update, or hyperbolic embedding layer whose dynamics cannot arbitrarily break quotient-space symmetries, potentially improving extrapolation across symmetry-related examples.

Useful5/10
Difficulty5/10
Novelty5/10
Paper: Rigidity on compact surfaces through hyperbolic symmetries arXiv:2607.05023
Unverified 2026

Relative-Difference Homotopy Consistency

Replace all pairwise consistency comparisons between m augmented views by a single group-valued relative-difference vector with m−1 components. Add a learned contractible-chart penalty so that the relative-difference map remains locally simple rather than merely numerically small. The construction is invariant to simultaneous left multiplication of every view, providing a useful gauge-invariant consistency signal.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Homotopic distances and group-like spaces arXiv:2607.03484
Unverified 2026

Invariant Möbius latent mixer

Insert a piecewise Möbius transformation as a deterministic latent mixing layer, using the paper's exact branch structure rather than a generic unconstrained MLP. The transformation repeatedly moves points between branches while preserving a known reference density, creating a cheap chaotic mixer with analytically computable Jacobian factors. Use a truncated, normalized version in practice so that the sigma-finite invariant measure becomes a valid finite training distribution.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Dynamics of integer zeroes of homogeneous quadratic equations over $\mathbb{R}^3$ arXiv:2607.03354
Unverified 2026

Pointwise Clarke-Tangent Training

Train a neural function under hard pointwise constraints by projecting its desired output-space update into the Clarke tangent cone of the admissible set at every sampled input. Fit the resulting feasible measurable direction with a parameter update instead of repeatedly allowing the network to violate constraints and repairing it with a penalty.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: The Clarke tangent and normal cones to decomposable sets in Lebesgue spaces arXiv:2607.03195
Unverified 2026

Modulated Scale-Residual Optimizer

Split the trainable state into an explicit scalar scale coordinate and a residual perturbation, then update them with separate time scales. Penalize residuals according to their distance from the scale-dependent core, so the optimizer cannot obtain apparent progress by destabilizing the scale mode. The method is a neural optimization analogue of the paper's modulation argument, not a direct consequence of the geometric singularity theorem.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Finite-Time Singularities of Lagrangian Mean Curvature Flow with Quantitatively Precise Dynamics arXiv:2607.03152
Unverified 2026

Barrier Geometry for Saturating Representations

Use the logarithmic exhaustion as a geometry for bounded hidden representations rather than only as a parameter constraint. A representation approaching the boundary receives an increasingly large metric, making ordinary Euclidean motion expensive and discouraging brittle saturation while preserving a bounded intrinsic gradient for the boundary coordinate.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Bottom of the Spectrum of Complete Kähler Metrics from Finite-Mass Plurisubharmonic Exhaustions arXiv:2607.03036
Unverified 2026

Floating-Body Robust Embedding Core

Construct a robust central region of each class or domain embedding cloud by intersecting halfspaces whose discarded cap mass is at most a prescribed fraction. Use this floating-body region to define prototypes or consistency targets, suppressing one-sided outliers without assuming Gaussian covariance structure. The centerpoint level 1/(d+1) provides a principled default depth parameter.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: From Ham-Sandwich to Centerpoints: Semialgebraic Algorithms for Cutting Polytopal Measures arXiv:2607.02400