ML: Embedding

Machine-learning ideas tagged Embedding in the ML taxonomy of the Math2NN corpus.

365 ideas found

Unverified 2026

Spatial-depth robust loss gating

Estimate the spatial distribution of minibatch embeddings using normalized residuals, then use the resulting spatial depth as a bounded confidence weight on each example's loss. Examples whose embeddings are spatially central receive near-unit weight, while isolated or adversarial examples are automatically downweighted without estimating covariance matrices or choosing a dimension-dependent bandwidth.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Dimension-invariant uniform consistency of the empirical spatial distribution function and its associated spatial depth estimator arXiv:2607.16092
Unverified 2026

Holonomy-Fixed State Filter

Add a preprocessing and inference module to a permutation-labeled graph network that computes the states globally compatible with all cycle transports. The module masks node or root-state logits to this fixed-point set, replacing exponential global assignment search with graph traversal plus permutation-table operations. A soft version can use the fixed-point mass as an auxiliary compatibility regularizer during training.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: Contextual Fraction on Permutation Gain Graphs: Exact Algorithms, Query Lower Bounds, and Dynamic Maintenance arXiv:2607.16037
Unverified 2026

Sneak-Path-Coded Quantized Weights

Store quantized neural-network weights in ReRAM using GF(4)- or GF(8)-based constrained blocks rather than writing raw symbols. The encoder selects codewords whose local patterns cannot create the most damaging short rectangular sneak paths, while a decoder reconstructs the original quantized symbols after sensing. This targets persistent edge-model storage and memristor crossbar weight loading, where reducing read errors may be more valuable than the coding-rate loss.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Current Should Not Sneak: Constrained Codes for Reliable Memristor Crossbar Arrays arXiv:2607.15929
Unverified 2026

Variable-Exponent Fourier Block

Replace a fixed-norm Fourier feature layer by a Fourier transform followed by spatially varying modular normalization. Use a baseline exponent approaching the endpoint regime at large coordinates and permit only bounded, smooth deviations so the transform remains controlled while the network can emphasize localized details.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Fourier inequalities in variable Lebesgue spaces arXiv:2607.15922
Unverified 2026

Fractal Sobolev Fourier features

Replace an isotropic Fourier-feature map with a fractional low-pass map whose order is selected from the estimated intrinsic Frostman dimension of the training samples. The layer represents a coefficient vector f in the ambient domain, applies the multiplier |k|^{-s}, and evaluates the smoothed function on the observed fractal-like data support. The theorem provides a geometry-dependent bound preventing high-frequency coefficient energy from producing arbitrarily large responses on concentrated…

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Orthonormal Sobolev estimates with fractal measures arXiv:2607.15826
Unverified 2026

Hadamard fractal Fourier encoding

Construct positional features from a self-similar digit system whose Fourier characters are orthogonal under a prescribed nonuniform measure, rather than sampling frequencies independently. Use several admissible multiplier values to create frequency bands while preserving the underlying Hadamard structure, giving a deterministic multiscale encoding with a better-conditioned feature Gram matrix on fractal or highly clustered coordinates.

Useful5/10
Difficulty4/10
Novelty5/10
Paper: Spectral eigenvalue set of self-similar measures associated with product-form Hadamard triples arXiv:2607.15743
Unverified 2026

RPA Phase-Separation Regularizer

Treat batches of samples, modalities, or MoE experts as components of a differentiable mixture and add the paper's topology-sensitive RPA free energy to the training objective. Learn a low-dimensional topology descriptor for each component, map it to an effective structure factor, and use the resulting free energy either to promote specialization or to penalize unwanted phase separation in representations.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: How Topology Shapes the Phase Behavior of Polyelectrolytes arXiv:2607.15703
Unverified 2026

Snowflake negative-type similarity regularizer

Augment a representation-learning objective with penalties enforcing the paper's four-point metric inequalities, and use an exponential snowflake kernel instead of unconstrained dot-product similarity. The experiment tests whether geometrically valid similarities improve retrieval or attention stability at equal model size and compute.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Lorentzian polynomials and matroids over triangular hyperfields 2: Analytic aspects arXiv:2607.15375
Unverified 2026

Defect-Localized Cycle Positional Encoding

Use the isolated positive spectral mode created by a finite branch defect on an otherwise long cycle as a graph positional feature. The feature should concentrate around structurally unusual vertices while remaining insensitive to the total cycle length, providing a principled alternative to raw Laplacian eigenvectors for cycle-with-branch graphs.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: Discrete Einstein metrics on unicyclic graphs arXiv:2607.14748
Unverified 2026

Polar-Gauge SPD Feature Layer

Replace a locally oriented three-channel feature frame by its positive-definite polar factor, removing arbitrary SO(3) basis rotations before the feature enters an MLP, attention block, or graph message-passing layer. Process the resulting SPD matrix in log coordinates so the downstream network receives a globally unconstrained symmetric representation rather than a gauge-dependent frame.

Useful5/10
Difficulty4/10
Novelty5/10
Paper: A Self-Dual Frame Formalism of the SO(3) Yang-Mills Theory arXiv:2607.14204
Unverified 2026

Main-Krylov Structural Encoder

Add a structural positional channel formed from the Krylov sequence generated by the graph adjacency matrix and the all-ones vector. For graphs with k main eigenvalues, this sequence has rank k, so a GNN can retain all information obtainable from global walk counts using only k node features rather than storing many adjacency powers.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Trees with exactly three main eigenvalues arXiv:2607.13577
Unverified 2026

Nonlinear torsion positional encoding

Compute a positive nonlinear torsion function on each input graph and append it to node features or use it to gate message passing. Unlike degree or ordinary Laplacian coordinates, the p-torsion field measures response to a uniform source and can expose global distance-to-boundary and bottleneck structure in a single scalar channel.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: On the p-torsional rigidity of compact metric graphs: a sharp Kohler--Jobin inequality arXiv:2607.12333
Unverified 2026

Crystal-Orbit Consistency Regularization

Generate structured augmentations of categorical sequences using the paper's adjacent crystal rewrites, then enforce prediction consistency across the resulting orbit. Unlike arbitrary random swaps, the rewrite preserves paired subsequences and modifies only the unmatched portion, making it appropriate for exchangeable discrete codes or explicitly permutation-equivariant inputs.

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Contractions and applications of crystal skeletons: Young quasisymmetric and Stanley symmetric functions arXiv:2607.12232
Unverified 2026

Absolute-Convex-Hull Diversity Regularizer

Regularize a learned set of vectors by maximizing the log-determinant of its frame operator, thereby maximizing the paper's sharp determinant-based upper bound on the volume of the centrally symmetric polytope generated by those vectors. The penalty encourages the vectors to span representation space isotropically and provides a global alternative to pairwise orthogonality losses.

Useful5/10
Difficulty3/10
Novelty4/10
Paper: The maximal volume of projections of the cross-polytope arXiv:2607.12072
Unverified 2026

Cyclotomic-Quotient Phase Embedding

Build a deterministic complex-valued embedding for discrete IDs by evaluating finite-field polynomials through an additive character, but learn coefficients only for one representative of each Frobenius or cyclotomic orbit. The quotient removes parameters that generate exactly the same feature function after the trace map, avoiding flat optimization directions and reducing the size of the embedding layer.

Useful5/10
Difficulty6/10
Novelty9/10
Paper: Exact Cardinality And Nonredundant Parametrization Of Character-Polynomial Codes arXiv:2607.11595
Unverified 2026

Schatten Distance Fingerprint Regularizer

Represent tokens, features, or attention states by normalized rank-one matrices and train the network to preserve their Schatten-​p distance profiles over complex phase rotations. Because the paper proves that equality of all distances \(\|\lambda e-v\|_p\) identifies \({\rm Tr}(e^*v)\), this regularizer preserves matrix overlap geometry under a learned transformation.

Useful5/10
Difficulty6/10
Novelty8/10
Paper: Tingley's Problem for Schatten \(p\)-Classes, $0<p\ne 2<\infty$ arXiv:2607.11244
Unverified 2026

Multiset Distance Positional Encoding

Add a permutation-invariant positional channel to a graph neural network by encoding each node through the histogram of shortest-path distances to a selected landmark set. Unlike standard ordered landmark distances, this representation is unchanged when landmarks are permuted and can be optimized to reduce node collisions. Use a small learned projection of the histogram alongside ordinary node features, with an optional collision penalty during training.

Useful5/10
Difficulty5/10
Novelty4/10
Paper: Multiset resolvability parameters in graphs: A survey with new results and open problems arXiv:2607.10311
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

Interleaving-consistent point-cloud features

Regularize a point-cloud or graph neural network so that two augmented versions of the same sample induce filtered proximity graphs with approximately interleaved Reeb graphs. The network is encouraged to preserve multiscale connectivity in learned scalar features, not merely pointwise feature similarity or final predictions. Use an approximate interleaving loss for small graphs and the cheaper H0 persistence-distance surrogate for larger batches.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Building confidence regions for Reeb graphs using the interleaving distance arXiv:2607.08458
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

Compact Abelian Graph Positional Codes

Replace one-hot node IDs or large positional encodings in a GNN with coordinates from a compact abelian Cayley graph. The coordinates preserve graph-shortest-path geometry exactly, while Fourier characters of cyclic factors provide smooth neural features with fewer channels.

Useful5/10
Difficulty7/10
Novelty7/10
Paper: Dimension and Order Bounds for Isometric Embeddings of Graphs into Abelian Cayley Graphs, and the Abelian Dividend arXiv:2607.07939
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

Lower-bound-guided binary latent bottlenecks

Use the paper's one-bit compressed-sensing lower bound to choose the number of binary latent measurements and to set a nonzero achievable-error floor during training. A sign bottleneck should not be given an unrealistically small bit budget: for approximately sparse latents, the target reconstruction error scales no faster than a power of effective sparsity divided by the number of sign measurements.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Near-Optimal Lower Bounds on One-Bit Compressed Sensing of Approximately Sparse Signals arXiv:2607.06750