2581 valuable arXiv mathematics papers the pipeline has analyzed — each with a short note on what its math gives to machine learning.
The paper supplies a compactness template for families of Hilbert-valued functions on a compact group: control small translations, suppress high Fourier modes, and, in infinite-dimensional feature spaces, enforce uniform tightness in the…
The paper introduces a robust Wasserstein barycenter by applying the Huber loss to each transport displacement before aggregation, rather than applying a robust loss to the final Wasserstein distance. This preserves quadratic sensitivity…
The transferable contribution is a topology-level optimization strategy for expensive nonlinear network substrates: predict physical or computational behavior from cheap graph descriptors, then search graph space instead of repeatedly…
The paper provides a deterministic alternative to random Johnson–Lindenstrauss matrices: generate projection coefficients from a reproducible Pisot beta-transformation orbit whose correlations decay geometrically because of the map's…
The paper gives a sharp, constructive relationship between the covariance of a lattice fundamental domain and the lowest nonzero Fourier/Laplacian frequency of the associated flat torus. Its transferable asset is a geometric certificate…
The paper offers a transferable mechanism for preventing neural ODEs from fitting trajectories with unconstrained or redundant parameters: embed the neural component analytically in the vector field, integrate parameter sensitivities…
The paper proves that a Shilnikov–Hopf unfolding can contain persistent strange attractors with SRB measures, despite alternating with parameter windows containing superstable periodic orbits. Its transferable mechanism is a rank-one…
The paper identifies a precise three-wave interaction geometry in Fourier space. After removing the linear Schrödinger evolution, each quadratic interaction is multiplied by an oscillatory phase with mismatch R(xi,xi_1); interactions with…
The paper supplies an explicit prescribed-performance recursion for higher-order error dynamics: bounding the highest filtered error inside a shrinking funnel forces every lower-order filtered error to remain inside computable funnels. The…
The paper's transferable asset is an adjoint weak formulation for fractional operators: instead of differentiating noisy measurements, it moves the fractional derivative onto smooth test functions and evaluates an integral against the…
The paper characterizes topological shadowing for finite-dimensional linear dynamics through a hyperbolicity condition: eigenvalues must avoid the unit circle, so the system decomposes into stable and unstable modes without marginal…
The paper introduces a finite spiking network whose firing threshold is driven by a signed, cumulative reinforcement state rather than by a fixed or exponentially decaying adaptation variable. The transferable asset is the separation…
The paper develops a weighted nuclear elastic-net estimator for drift matrices in continuously observed Ornstein-Uhlenbeck systems, addressing ill-conditioning caused by low-rank and non-ergodic dynamics. Its transferable asset is…
The paper offers a constructive method for continuing regime-transition curves directly from time-dependent simulations rather than deriving bifurcation equations: define scalar features of late-time trajectories, identify regular…
The paper turns directional feature aggregation into a smooth analysis operator: environment or feature signals are integrated against nonnegative softmax weights forming a partition of unity. Its transferable asset is not softmax itself…
The paper’s central transferable mechanism is a deletion-counterfactual definition of learned value: a memory state is useful only when an informed agent with read access outperforms a blind agent that has the read port removed and…
The paper provides a constructive mechanism for systems with several intermittently neutral fixed points: trajectories can spend power-law residence times near different fixed points, while a pressure variational principle selects between…
The paper develops an asymmetric, measure-aware notion of functional domination: a target family of observables is considered representable by a source family when, under a coupling, almost all mass lies on pairs where every target…
The paper develops a constructive low-dimensional range-finding method for estimating fixed-component Gaussian mixtures without separation or minimum-weight assumptions. Its transferable asset is the decomposition of high-order Hermite…
The paper develops a determinant-based volume polynomial for zonotopes, where each coefficient measures the geometric diversity of a subset of generating vectors. Its central structural result identifies log-submodularity with the Rayleigh…
The paper identifies a useful local regime for equality-constrained nonconvex optimization: the Gradient-Eigenstep method becomes ordinary gradient descent on Fletcher's augmented Lagrangian when the iterate is near a strong second-order…
The paper provides a constructive activity-gated spreading dynamical system on a weighted directed graph, where source-node activity multiplicatively rescales outgoing messages and a saturation term prevents unbounded growth. This…
The paper offers a transferable robust control-barrier-function mechanism rather than merely a battery-specific controller: a learned estimate of an unmeasured safety state is inserted into a higher-order barrier constraint, and a…
The paper's transferable asset is spectral group sparsity defined over complete Laplace eigenspaces rather than individual eigenvectors. Grouping an entire repeated eigenspace makes the representation invariant to arbitrary rotations…