2581 valuable arXiv mathematics papers the pipeline has analyzed — each with a short note on what its math gives to machine learning.
The paper provides a variational principle for the complexity of inverse trajectories in non-invertible dynamical systems: global preimage entropy equals the supremum of empirical preimage entropy over invariant empirical-measure classes…
The paper contributes an executable way to convert a convex lower-level optimization problem into a single nonlinear program by combining conic canonicalization, KKT conditions, and complementarity-gap continuation. This is transferable to…
The paper's transferable mechanism is jump-conditioned feedback: an event-dependent completely positive map changes the post-event state while preserving explicit accounting of fluctuations, Fisher information, and information-processing…
The paper gives an unusually strong distributional invariance for a deterministic reciprocal-projection construction: any simplex-weighted collection of nonzero directions produces an output whose squared cosine with the input is exactly…
The paper introduces a preference-aware graph coloring equilibrium: vertices receive distinct colors from adjacent vertices, while directed cycles of mutually profitable color exchanges are forbidden. This is transferable to graph…
The paper provides an operator-valued comparison principle for completely positive maps: instead of collapsing a divergence to a scalar immediately, it constructs a self-adjoint operator in the codomain using a noncommutative perspective…
The paper identifies a concrete replacement for Monte Carlo random features: approximate the kernel's integral representation with a deterministic quadrature rule chosen to preserve the spectrum of the finite-data Gram matrix. The…
The transferable asset is the paper's parametrix treatment of state-dependent diffusion: instead of approximating a variable-coefficient parabolic operator directly, freeze the diffusion locally, apply an exactly computable Gaussian…
The paper provides a transferable compositional stability mechanism: input-output differential passivity (IODP), certified using local Jacobian inequalities and a quadratic differential storage matrix. Unlike equilibrium-specific Lyapunov…
The paper provides a constructive recipe for representing operators on changing surfaces in one fixed function space: a surface contravariant Piola map transports geometry-dependent Maxwell trace spaces to a reference space, while Jacobian…
The paper develops differentiable pushforward dynamics on Wasserstein space. At an invariant measure, the derivative is a transfer operator acting on perturbation vector fields followed by orthogonal projection onto the Wasserstein tangent…
The paper develops a constructive way to replace exponentially many activation scenarios by a conservative polyhedral inner approximation built from reusable exchange patterns. Its key asset is a one-sided decomposition inequality: if a…
The paper provides a concrete fast-weight associative memory update that separates retrieval from plasticity: the model reads a pre-update memory state and only then writes the current key-value association. The transferable asset is a…
The paper derives higher-gradient field dynamics from a concave entropy rather than a higher-time-derivative Lagrangian, yielding a first-order gradient flow with a Lyapunov function and a negative relaxation spectrum. The transferable…
The transferable asset is not the particular Navier–Stokes solver, but its meshfree intrinsic calculus for vector fields stored on irregular samples of a curved manifold. Tangent projection provides a simple way to prevent neural outputs…
The paper provides an exact spectral mechanism for non-Hermitian matrices with transposition symmetry: after factoring out a Vandermonde term, the joint eigenvalue density is a Calogero-model scattering wavefunction with inverse-square…
The paper provides an exact large-N duality between Hermitian and non-Hermitian random-matrix level statistics, organized by transposition symmetry rather than only conventional time-reversal symmetry. Its transferable asset is a…
The paper derives a coarse-grained fluctuating hydrodynamics in which a conserved density evolves through a current with density-dependent diffusivity and multiplicative noise, rather than through a linear Gaussian diffusion equation. Its…
The paper gives a constructive mechanism for deterministic amplification of arbitrarily small asymmetries: a finite-domain growth event has a survival time determined by an integrated coverage hazard, and the resulting facet velocity…
The paper provides a concrete failure taxonomy for Bayesian tracking under model misspecification: the posterior can depin and become diffuse, or remain sharply localized while concentrating on the wrong state. Its transferable asset is…
The paper offers a constructive replacement for memoryless control-barrier operators with proper space-time kernels that attenuate high-frequency measurement noise while retaining affine dependence on the control input. Its central…
The paper gives a sharp finite-sum complexity law showing that the useful restart schedule for PAGE depends qualitatively on whether the PL condition number is below or above the square-root sample-size threshold. This is transferable as a…
The paper gives a constructive method for generating translation-invariant matrix-product states that are exact zero modes of constrained Hamiltonians. Its transferable asset is the combination of a hard global validity projector with…
The paper proves a quantitative mass-versus-first-variation inequality for rectifiable anisotropic varifolds in arbitrary codimension. Its transferable asset is a geometric feasibility certificate: a surface with substantial mass cannot…