Math: Geometry

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

631 ideas found

Unverified 2026

Hermitian ETF classifier head

Construct a classifier whose normalized class vectors form an explicit 2d-line equiangular tight frame instead of using independently initialized weights. The ETF gives every class the same norm, equal pairwise coherence, and an isotropic frame operator, which should make final-layer gradients better conditioned and reduce accidental class crowding. The classifier can be fixed, or restricted to a learned unitary rotation of the ETF so that its geometry is preserved during training.

Useful5/10
Difficulty4/10
Novelty4/10
Paper: New constructions of optimal arrangements of $2d$ lines in $\mathbb{C}^d$ arXiv:2608.16116
Unverified 2026

Corner-Snowflake Metric Learning

Add a metric-learning loss whose local geometry changes according to several learned or supplied boundary coordinates. Use a product conformal factor when violations of multiple constraints should accumulate, or a sum conformal factor when the most severe constraint should dominate; on a face where several coordinates vanish, impose the corresponding snowflake exponent on tangential distances.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Metric Completion and Boundary Geometry of Multi-Weighted Conformal Metrics on Manifolds with Corners arXiv:2608.15540
Unverified 2026

Quasi-analytic response head

For a neural model predicting a scalar response as a function of a continuous dynamical parameter, replace an unconstrained MLP output head by an analyticity-constrained spectral head. Train it on observations covering a positive-measure subset of the parameter interval and regularize the remaining coefficients so that the learned response satisfies a quasi-analytic derivative-growth bound; the intended benefit is reliable continuation from sparse parameter coverage rather than ordinary…

Useful5/10
Difficulty4/10
Novelty8/10
Paper: Rigidity of Mather's $β$-function on a KAM set for analytic billiards-like maps and unique quasi-analytic continuation arXiv:2608.15401
Unverified 2026

Singularity-isolated cell interaction layer

Replace pointwise pair interactions between mesh cells by quadrature of the interaction kernel over the full Cartesian product of the two cells. Decompose each cell pair into convex-hull pieces and apply a Duffy-like radial transformation so the coincidence singularity is confined to one quadrature coordinate, allowing fixed Gauss-Jacobi or adaptive quadrature to produce smooth, low-variance interaction features.

Useful5/10
Difficulty7/10
Novelty7/10
Paper: Space-Time Galerkin Boundary Element Method for the Wave Equation arXiv:2608.15292
Unverified 2026

Critical 2d Intensity Bottleneck

Replace a complex latent vector x in C^d by squared magnitudes of m learned complex linear projections. Set m equal to 2d: the paper proves that m less than or equal to 2d minus 1 cannot generically preserve the latent up to global phase, whereas m equal to 2d is generically sufficient, giving a principled minimal width for a phase-invariant neural bottleneck.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: The Minimum Number of Measurements for Almost-Everywhere Complex Phase Retrieval arXiv:2608.15003
Unverified 2026

Hypercube-balanced routing regularizer

Represent the eight experts or channels in a block as the vertices of a 3-bit hypercube and compute their average nonnegative routing masses. Add a regularizer that rewards a large ratio between the product of the six coordinate-facet sums and the mixed triple/pair polynomial from the theorem. This explicitly encourages routing distributions that remain visible under all three binary projections, rather than merely maximizing entropy or balancing experts marginally.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: On the Log-submodularity for zonoids: from Mixed Volume inequalities to the Hypercube arXiv:2608.14909
Unverified 2026

Convex-mixture graph Langevin optimizer

Put a gradient-Gibbs prior on differences between connected neural parameters rather than on individual parameters, and evolve the parameters with Langevin steps generated from randomly selected strictly convex component energies. The aggregate regularizer may be non-convex, but every sampled component has controlled curvature and outward drift, providing a practical stability mechanism for noisy training.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Gradient Gibbs measures with non-convex potentials and the universality class of the Gaussian Free Field arXiv:2608.14526
Unverified 2026

Spherical anti-additive-collision embeddings

Constrain an embedding table to the unit sphere and penalize repeated or nearly repeated pair sums. This discourages additive quadruples a+b approximately equal to c+d, reducing unwanted linear structure and making distinct tokens less interchangeable under downstream composition. The theorem provides a geometric target: on a sphere, the affine-line concentration factor is bounded by two, so exact additive energy should scale close to n squared rather than the much larger values produced by…

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Near diagonal additive energy bound for points on algebraic surfaces arXiv:2608.14467
Unverified 2026

Analytic Gaussian Measurement Bottleneck

For a neural model whose outputs lie on a d-dimensional analytic family in a very high-dimensional space, replace the full output vector by 2d+1 or a modestly oversampled number of fixed Gaussian scalar measurements. The paper's theorem predicts almost-sure injectivity in the noiseless setting, so an inverse network or decoder can recover the same latent instance without processing the full observation. Because the theorem does not provide a noise-stability constant, use M=4d+8 or M=8d in the…

Useful5/10
Difficulty4/10
Novelty5/10
Paper: Analytic inverse problems with finitely many random measurements arXiv:2608.14324
Unverified 2026

Jordan spectral feature scaling

Group neural features into small Hermitian matrix elements and scale each group with the paper's tracial spectral Lp norm rather than independently normalizing scalar channels. This introduces a coupled spectral geometry while remaining implementable with ordinary eigendecompositions in the associative Hermitian-matrix special case.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Spectral nonassociative $\mathrm{L}^p$-spaces for $\mathrm{JBW}^*$-algebras arXiv:2608.14231
Unverified 2026

Velocity-Scaled Symbolic Flow Model

Represent a continuous-time neural dynamical system as a symbolic Markov chain over regions together with a positive learned roof function giving the time spent in each region. Weight local reconstruction and prediction errors by the predicted vector-field speed, following the paper's scaled Hölder coding relation, so that the model does not over-penalize arbitrarily small coordinate errors near equilibria. This produces a hybrid latent model with discrete long-range structure and continuous…

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Symbolic dynamics for non-uniformly hyperbolic flows arXiv:2608.14095
Unverified 2026

Heat-Wasserstein curvature preconditioner

Replace a Euclidean feature-space metric by a short-time heat-kernel/Wasserstein metric and use it to precondition updates or penalize distortions of local neighborhoods. The first-order correction is a Ricci-curvature term, while the second-order residual captures curvature variation and quadratic curvature effects that ordinary diffusion smoothing misses.

Useful5/10
Difficulty7/10
Novelty7/10
Paper: Second-Order Departure of the Gigli--Mantegazza Flow from Ricci Flow arXiv:2608.14039
Unverified 2026

Hardy-Basis Equivariant Mixer

Insert a fixed or partially learnable equivariant change-of-basis module into a spherical or SO(3)-equivariant network. At each angular frequency \(\ell\), the module maps the line selected by the line-bundle quantization to the line selected by the Grauert-tube quantization, allowing the network to represent both holomorphic/base-local and geodesic-flow-adapted features without breaking rotation equivariance.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Intertwining the line bundle and Grauert-tube Hardy quantizations of the round 2-sphere arXiv:2608.13965
Unverified 2026

Warm-start hit-and-run augmentation

Replace rejection sampling or short biased random walks inside a convex latent constraint set with hit-and-run. At each step, choose a uniformly random direction and sample uniformly along the entire chord through the current point; the paper's mixing result predicts that a chain initialized by a crude approximate sampler becomes close to uniform with only logarithmic dependence on initialization bias and target error.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Hit-and-Run Mixes as Fast as the Ball Walk arXiv:2608.13487
Unverified 2026

Spectral-gap covariance control for latent representations

Use the flat-torus covariance bound as a representation regularizer that controls the largest covariance eigenvalue while maintaining a prescribed total variance. This creates a directional anti-collapse constraint rather than only a scalar variance penalty, and can be applied to encoder outputs, VAE latents, or Transformer sequence representations.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: Spectral and Isoperimetric Bounds on Flat Tori arXiv:2608.13052
Unverified 2026

Convex-lifted additive codebook

Encode each scalar or discrete code t by the strictly convex lift γ(t)=(t,t²), optionally followed by a learned linear projection and normalization. Because three-code sums on this curve have only near-minimal additive energy, the representation should produce fewer collisions when a model composes three tokens, codes, or retrieved items by addition.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Near optimal three-fold additive energy bound for points on convex curves arXiv:2608.12316
Unverified 2026

Newton-polygon anisotropic spectral regularizer

Regularize a spatiotemporal neural model with spectral penalties corresponding to several temporal-spatial scaling laws rather than using a single isotropic smoothness penalty. The model can remain spatially detailed while suppressing temporal oscillations, or learn the opposite preference when the data demand it.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: An $L^p$-Theory for Time-Periodic Mixed-Order Partial Differential Equations under General Boundary Conditions arXiv:2608.12250
Unverified 2026

Husimi spectral concentration regularizer

Apply a convex Husimi functional as a differentiable regularizer to positive matrices used by attention heads, routers, or feature covariances. Penalizing the squared response suppresses sharp spherical peaks and can prevent collapsed routing or unstable attention without directly forcing uniform eigenvalues.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Isospectral majorization and isoperimetric inequalities for coherent states on the Bloch sphere arXiv:2608.12248
Unverified 2026

Pisot-Separated Multiscale Codes

Replace an unconstrained geometric multiscale codebook by features generated from a finite digit set and a Pisot scale factor. The contracting algebraic-conjugate directions should suppress near-collisions between representations at different scales, producing a discretely separated hierarchy that can be used for embeddings, recurrent memory, or quantized transformer states.

Useful5/10
Difficulty6/10
Novelty9/10
Paper: Self-similar Delone sets and Pisot numbers arXiv:2608.11867
Unverified 2026

Beckner spectral logit regularizer

Represent an axially symmetric neural field on the sphere as a scalar function of latitude and regularize it with the paper's Paneitz energy together with its exponential log-partition term. Enforce a center-of-mass condition on the normalized exponential density so that the regularizer cannot be reduced by simply translating the field toward a first spherical-harmonic mode.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Sharp Beckner's Inequalities for Axially Symmetric Functions on $\mathbb{S}^N$ arXiv:2608.11126
Unverified 2026

Gaussian Moment-Window Activation Regularizer

Whiten intermediate feature vectors and constrain several gauge moments to remain in the dimension-dependent interval predicted by the paper's Gaussian/log-concave comparison. Apply the penalty only to moderate orders, where the paper gives a uniform bound independent of the particular log-concave distribution; this should suppress heavy activation tails without forcing all features to be exactly Gaussian.

Useful5/10
Difficulty3/10
Novelty6/10
Paper: Moment comparisons, Sudakov inequalities and entropy of centroid bodies arXiv:2608.10853
Unverified 2026

Lorentzian coefficient router

Represent a small expert router or attention interaction by a homogeneous polynomial with nonnegative coefficients, then penalize violations of the Lorentzian Hessian signature on degree-two derivative slices. Initialize or warm-start the coefficient tensor from a normalized skew-Schur coefficient array, which the paper identifies as a realizable volume polynomial and therefore a structurally valid Lorentzian point.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Richardson volume models for skew Schur and skew Schur $P/Q$-functions arXiv:2608.10516
Unverified 2026

Subgaussian orthogonal feature basis

Add a learnable orthogonal rotation to a hidden representation and train it to make every channel projection have a small ψ2/L2 ratio. Unlike variance normalization, this explicitly suppresses directions with unusually heavy empirical tails while preserving the total quadratic energy of the representation.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Geometry of the subgaussian body of an isotropic convex body arXiv:2608.10241
Unverified 2026

Asymmetry-Aware Bochner–Riesz Graph Filter

Replace a sharp graph-Laplacian spectral filter with a Bochner–Riesz filter whose smoothness exponent increases when the graph contains regions with different effective dimensions. Estimate the largest local dimension and dimension gap from neighborhood growth, then choose the exponent above both the classical spectral threshold and the asymmetric obstruction threshold. This should suppress unstable high-frequency mixing in heterogeneous graphs while preserving more low-frequency signal than…

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Herz versus Fefferman: Symmetric and asymmetric Bochner--Riesz theory arXiv:2608.09247