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 lightweight rule for adapting the training-only slope of a spiking neuron's surrogate derivative from transformer attention uncertainty. Its transferable asset is the use of normalized attention entropy as a…
The paper gives a sharp pointwise bound on the pullback metric of a V-harmonic map, improving the usual quadratic dilatation estimate through a piecewise function of the generalized dilatation order. This transfers to neural encoders as a…
The paper develops a non-Abelian extension of KPZ dynamics in which a phase-like chronon couples to multiple Goldstone sectors. Its transferable mechanism is an RG-predictable relevance boundary: nonequilibrium couplings are relevant below…
The paper identifies a concrete nonequilibrium mechanism in which compact phase variables support spacetime vortices, while phase-shift symmetry creates a homogeneous fixed point that suppresses vortex nucleation. The competition between…
The paper gives an exact minimax result for passive adaptive control with an unknown scalar gain and bounded adversarial disturbances. Its transferable mechanism is consistent-set model chasing: maintain the set of parameters compatible…
The paper isolates a useful decomposition of connectivity control into local interactions plus a global node embedding, and proposes replacing the difficult Fiedler vector with the dominant eigenvector of the weighted adjacency matrix. The…
The paper supplies a discrete concavity calculus on triangular arrays: hive values satisfy three local rhombus inequalities, while the octahedron recurrence converts between alternative boundary representations using max-plus updates. This…
The paper provides two transferable geometric mechanisms: a trajectory-space metric that measures the maximum separation over a unit-time rollout, and stable magnetic B-functions whose level sets form asymptotic stable foliations. The…
The paper provides a transferable safety mechanism rather than merely a quadrotor controller: a decentralized navigation-force policy is passed through a robust higher-order control-barrier-function quadratic program (HOCBF-QP) that…
The paper offers a transferable, variationally consistent way to learn a three-dimensional thermodynamic functional from equilibrium density fields rather than supervised free-energy or chemical-potential labels. Its key transferable…
The paper gives a sharp functional on spherical fields that combines a spectral Sobolev energy with an exponential concentration term. Its transferable asset is the explicit conformally natural operator P_N, whose spherical-harmonic…
The paper gives a constructive sampling method with a strong warm-start guarantee: hit-and-run reaches near-uniformity on an isotropic convex body with only logarithmic dependence on the warmness and accuracy parameters. The transferable…
The paper develops a mixture-aware construction for transporting probability mass by augmenting continuous states with component labels and applying component-specific Markov kernels. This structure can become a generative sampler that…
The paper replaces vertex-tuples by tuples of vertex subsets, yielding a dense analogue of Weisfeiler–Leman that can distinguish structures invisible to ordinary message passing on dense graphs. Its most transferable object is the…
The paper introduces nonlinearity-subtracted DMD (NSDMD) for systems of the form \(\dot{x}=Ax+f(x)\), where the nonlinear contribution \(f\) is available from physics or a simulator but the linear operator \(A\) is unknown. NSDMD subtracts…
The paper offers a transferable robust-design mechanism: optimize an information or space-filling criterion averaged over a population of plausible dynamical models rather than for one hypothesized model. Its practical asset is stochastic…
The paper identifies a universality mechanism in which permutation symmetry across interchangeable units, together with vanishing per-unit gradients at zero, forces the leading near-initialization computation to depend on weights through…
The paper constructs divergence-free Stratonovich transport noise for reaction-diffusion systems and proves that it can preserve classical solvability while enhancing dissipation of spatial fluctuations at a tunable exponential rate. The…
The paper develops input-to-state stability (ISS) certificates for time-varying mass-action reaction networks, including weakly reversible networks with nonzero deficiency and multiple linkage classes, and some non-weakly-reversible…
The paper gives an explicit theory for changing the dimension of spherical metric representations while controlling worst-case pairwise angular distortion. The most transferable asset is the compositional rule for synchronized spherical…
The paper contributes a concrete multi-stream residual architecture whose inter-stream mixing matrix is constrained to the Birkhoff polytope of doubly stochastic matrices, rather than learned without constraints. This provides a…
The paper gives an explicit positivity-and-stability design principle for diffusion dynamics controlled through boundary conditions: negative boundary gains are necessary and sufficient for exponential stability of the coupled…
The paper gives a constructive sensitivity and conditioning theory for entropic OT layers whose costs are linear in features. Its main transferable asset is a spectral sandwich that turns plan probabilities, entropy strength, and feature…
The paper isolates an explicit finite-size quadratic contribution to the log-determinant of Toeplitz matrices whose log-symbol has only 1/|k| Fourier decay, while showing that each fixed higher-order term remains bounded. This suggests a…