ML: Mlp

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

408 ideas found

Unverified 2026

Polyconvex rotation-frame Jacobian loss

Replace ordinary Jacobian penalties in coordinate MLPs or deformation networks with a learned local rotation frame and a polyconvex energy of the relative stretch. Penalize \(U\), its cofactor, and its determinant through a convex function, while separately smoothing the rotation field through \(R^T\operatorname{Curl}R\). The intended benefit is resistance to fold formation and better conditioning than directly penalizing \(\|J-I\|^2\), especially for large deformations.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: Polyconvexity for Cosserat nonlinear elasticity and nonlinear couple-stress theory arXiv:2608.23072
✓✓ Beats tuned baseline 2026

Boundary-Compressed Approximate Pruning

Use an approximate decision diagram to select a structured subset of neurons, channels, attention heads, or attention edges when their quadratic interactions are sparse or inverse-sparse. Merge states that agree on a local interaction boundary and accept a tunable epsilon loss in the pruning objective, obtaining a representation whose size is linear in model width for fixed accuracy tolerance.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Convexification of mixed-integer quadratic optimization via decision diagrams arXiv:2608.22815
✓✓ Beats tuned baseline 2026

Cyclic Lie-Bracket Residual Block

Replace one deterministic residual update with a short cyclic composition of learned vector fields evaluated for randomized, short run times. Because finite compositions of noncommuting flows generate directional-derivative and Lie-bracket terms, changing the cycle order gives the network an explicit, low-cost way to learn drift directions that are unavailable from the individual vector fields alone.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Diffusion limits of cyclic finite-velocity random motions along vector fields arXiv:2608.22514
Failed on benchmark 2025

Log-Scale Self-Similar Activation

Replace a conventional scalar activation by a geometrically indexed family of affine pieces whose slope changes with the logarithmic magnitude of the input. The same two endpoint parameters are reused across all scales, giving a compact, explicitly scale-aware activation that can represent different responses for exponentially separated activation magnitudes.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: From two-dimensional continuous maps to one-dimensional discontinuous maps: a novel reduction explaining complex bifurcation structures in piecewise-linear families of maps arXiv:2512.02291
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

Positive-Definite Quadratic Feature Pair

Replace two unconstrained scalar quadratic feature heads with a pair whose quadratic forms admit a positive-definite linear combination. This prevents the two heads from simultaneously vanishing on any nonzero hidden vector, which can reduce representation collapse and improve the conditioning of downstream gates or auxiliary objectives. The constraint can be implemented softly with a spectral-margin penalty, or exactly by parameterizing one learned pencil as positive definite.

Useful5/10
Difficulty4/10
Novelty8/10
Paper: Last two pieces of the puzzle for unsolvability of a system of two quadratic (in)equalities arXiv:2608.30571
Unverified 2026

Uniformly bounded Jacobi spectral features

Replace raw powers or unconstrained polynomial spectral features with normalized Jacobi features whose amplitude is provably bounded on the entire input interval. Use trainable mixtures of these features in a positional encoding, graph spectral layer, or MLP front end, while preserving the theorem's normalization and optionally constraining the learned mixture norm.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: The Koornwinder--Kostenko--Teschl Conjecture for Jacobi Polynomials and the Discrete Laguerre Phase Transition arXiv:2608.30486
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

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

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

Braid-word reversible mixer

Replace a dense token- or channel-mixing matrix with a product of local braid generators acting on adjacent coordinates. Each generator is an exactly invertible 2-by-2 transformation, while the braid and far-commutativity identities give multiple equivalent factorizations of the same global operator. This creates a sparse, reversible mixer with O(kn) cost for a braid word of length k, rather than O(n^2) cost for a dense matrix.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Fox $p$-Colorings as Fixed Points of Braid Representations arXiv:2608.29046
Unverified 2026

Banded Production-Matrix Polynomial Layer

Replace a dense learned polynomial-feature transform with a d-orthogonal recurrence whose production matrix is constrained to a (d+2)-banded lower-Hessenberg form. The layer generates successive features using only local recurrence coefficients, giving O(dN) arithmetic and O(dN) parameters for N basis functions instead of O(N^2) dense mixing.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Riordan array representation of recursive polynomial sequences, orthogonal polynomial sequences, and $d$-orthogonal polynomial sequences arXiv:2608.28834
Unverified 2026

Khintchine anti-degeneracy regularizer

Add a regularizer that rewards each neuron's expected absolute response to random sign perturbations, normalized by the neuron's l2 norm so ordinary weight scaling cannot trivially increase the objective. Use the paper's distance-sensitive Khintchine lower bound to penalize filters close to the two-coordinate extremal set, promoting distributed and perturbation-stable feature extraction.

Useful5/10
Difficulty3/10
Novelty8/10
Paper: A Two-regime Khintchine Inequality and an Improved Bound on the Degree-1 Fourier Weight for Linear Threshold Functions arXiv:2608.27908
Unverified 2026

Coherence-aware superposition bottleneck

Insert an overcomplete sparse feature bottleneck into an MLP or embedding stream: encode an activation h with z = ReLU(W^T h + b), then reconstruct or continue computation from Wz. Normalize dictionary columns and train them to remain nearly tight and low-coherence, while choosing a negative bias from an estimate of worst-case cross-feature interference. The hypothesis is that this gives cleaner, more stable feature supports than an ordinary L1 sparse autoencoder at the same latent width.

Useful5/10
Difficulty5/10
Novelty4/10
Paper: Towards a mathematical theory of superposition arXiv:2608.27540
Unverified 2026

Transverse Fourier Collision Control

Construct a Fourier layer whose active frequencies lie on several nonparallel polygonal patches or thin annular sectors, and cap repeated difference vectors generated by pairs of patches. The bounded-multiplicity geometry limits how many input frequency pairs can contribute to the same output frequency, potentially reducing spectral aliasing and gradient variance in nonlinear Fourier mixing.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: Quantitative Uniqueness and Rough Damping on $\mathbb T^2$ arXiv:2608.27544
Unverified 2026

Ward-Residual Model Selection

Train a neural approximation to a scale-dependent effective action, energy functional, or field while penalizing the residual of a known continuous-symmetry Ward identity. Select the regulator, smoothing scale, or architecture hyperparameter at the minimum Ward residual, and require that the residual decreases when model capacity or derivative-expansion order increases.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Convergence of the conformal Ward identity in the derivative expansion approximation arXiv:2608.25103
Unverified 2026

RG-monotone representation compression

Interpret successive neural representations as an RG flow and constrain coarse-graining layers to remove unstable or redundant information monotonically. The paper reports monotonic decrease of an effective central charge along measurement-induced RG flows; a neural analogue can use a measurable information-complexity proxy and reject compression steps that increase it while preserving task-relevant information.

Useful5/10
Difficulty6/10
Novelty6/10
Paper: Learning Potts Models and $Z_3$ Toric Codes: Higher and Ordinary Nishimori Criticality arXiv:2608.20268
Unverified 2026

Controllability-Rank Regularizer

Regularize learned skew generators so that their iterated Lie brackets span many independent feature-mixing directions rather than collapsing to commuting or redundant matrices. This turns the paper's controllability family into a differentiable diversity objective for structured neural layers.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Nonlinear Controllability and the Propagation of Local Information: From the Kalman Family to Lie Brackets, Rotation Groups, and Reachable Subgroups arXiv:2608.20094
Unverified 2026

Degree-Aware Tensor Concentration Clipper

Add a calibrated robustification rule after a symmetric polynomial feature map z(x)=vec(x^{\otimes d}). For a convex Lipschitz head or loss applied to z(x), compute a high-probability deviation radius from the paper's concentration rate and clip only examples beyond that radius. This explicitly accounts for the large radial fluctuations created by reusing the same vector in every tensor slot.

Useful5/10
Difficulty5/10
Novelty7/10
Paper: Sharp Convex Concentration for Symmetric Random Tensors with Subgaussian Coordinates arXiv:2608.19832
Unverified 2026

Cauchy-Torsion Concave Potential

Train a scalar neural field on a bounded convex domain with a restricted half-Laplacian residual and an explicit strict-concavity barrier. The paper's theorem motivates requiring the learned potential to have negative-definite Hessian throughout the domain, while the nonlocal residual gives the model a global Cauchy-process-style inductive bias rather than only local smoothness.

Useful5/10
Difficulty5/10
Novelty6/10
Paper: Strict Concavity of the Torsion Function for the Restricted Half-Laplacian in Bounded Convex Domains arXiv:2608.19586
Unverified 2026

Rearrangement Head-Tail Regularizer

Regularize hidden activations or per-example gradients with a discrete version of the paper's Z_E^2 norm. Apply an E-norm to the largest fraction of coordinates and an L2 norm to the remaining tail, allowing the model to preserve a few large responses while discouraging widespread heavy-tailed noise.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Isomorphisms between symmetric spaces over infinite and finite von Neumann algebras arXiv:2608.18460
Unverified 2026

Exterior-power truncation for 2D tensor channels

Use the dimension-specific relation A_3=0 to remove all intermediate channels transforming as the third exterior power of the two-dimensional vector representation. In tensor-product attention or equivariant MLPs, this is an exact algebraic pruning rule rather than approximate low-rank compression.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: The Brauer category $\mathcal{B}(2)$ has principal graph $D_\infty$ arXiv:2608.18328