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 constructive contraction-based address system: repeatedly selecting one of nine affine child maps produces nested compact cells whose diameters shrink geometrically, so every infinite address identifies exactly one…
The paper exposes a practically important mismatch between communication compression and Muon's matrix-valued Linear Minimization Oracle (LMO): elementwise sign compression after the polar/LMO step can ascend even on a linear objective…
The paper provides a Hamiltonian-level certificate for Yang–Baxter integrability: under its regularity and locality assumptions, the Reshetikhin condition is sufficient as well as necessary for constructing an integrable R-matrix…
The paper gives a constructive periodic exact-distance covering of the integer grid using a finite cyclic labeling, rather than merely proving that a sparse set exists. The transferable asset is a deterministic sparse connectivity pattern…
The paper offers two transferable mechanisms: continuation in inverse temperature from an analytically known infinite-temperature heat kernel, and symmetry-preserving flow parameterizations for learning a difficult density matrix. The most…
The paper gives a sharp robustness law for randomized Milstein integration when both coefficient evaluations and Wiener-path increments are noisy: the strong error is the sum of a discretization term and an unavoidable linear oracle-noise…
The paper's transferable contribution is to treat safety enforcement as a modification of the continuous generative vector field rather than as a post-hoc projection of the final action. This creates a useful interface for flow-based…
The paper turns multivariate stochastic dominance into a coupling feasibility condition that tolerates coordinatewise violations when they are compensated by sufficiently large improvements elsewhere. Its transferable asset is the…
The paper provides a constructive decomposition for backward dynamics that combine continuous evolution with discontinuous right jumps and reflection against an irregular lower obstacle. This suggests an event-driven residual or…
The paper's transferable asset is a constructive contraction-metric framework for learned nonlinear dynamics: instead of merely fitting trajectories, it learns a state-dependent metric and feedback law that quantify how model mismatch…
The paper's transferable asset is a robust aggregation principle: replace ordinary sample averages with quantile-winsorized averages, obtaining error that scales as the adversarial fraction to the power 1-1/m under finite m-th moments…
The paper establishes an affine-normalization principle: every convex body admits a linear image whose Euclidean covering entropy is controlled, up to universal constants, by that of the crosspolytope, while the optimal…
The paper provides an exact spectral-basis update for polynomially prepared initial states: replacing x_0 by Q(H)x_0 reweights the reference spectral measure by |Q|^2, and the new orthogonal-polynomial basis is connected to the old one…
The paper turns support-entropy arguments into finite, checkable certificates: failure of a uniform-marginal distribution on a coefficient support yields an explicit entropy gap rather than merely an asymptotic statement. This is…
The paper provides a higher-order random-walk mechanism on simplicial complexes, where incidence matrices couple simplices across dimensions and a teleportation term interpolates between local hopping and long-range exploration. Its…
The paper identifies a non-monotonicity failure in state-dependent admission control: rejecting work can lower the current workload, change later decisions, and thereby cause a larger future job to be admitted. The transferable asset is…
The paper identifies entropy production as a quantitative indicator of computational performance in driven reservoirs. Its transferable mechanism is the joint use of driven response and the discrepancy between driven and innate entropy…
The paper studies a continuous-time graph process in which infection spreads along infected-to-susceptible edges while infected nodes are removed at a rate proportional to their number of susceptible neighbors. This creates a competition…
The paper’s transferable mechanism is a quantitative mixing dichotomy for systems preserving an invariant foliation: correlation decay is governed by the slower of the quotient dynamics and the dynamics within the leaves. This suggests a…
The paper develops rational Jacobi rotations that approximately eliminate off-diagonal entries of a symmetric matrix while preserving exact orthogonality and the matrix inertia, avoiding the irrational coefficients produced by classical…
The paper provides a transferable split-conformal mechanism for turning a nominal dynamical predictor plus a learned state-dependent discrepancy into asymmetric, finite-sample-valid uncertainty sets. The key asset is directional…
The paper develops a localization principle for pseudospectra of banded operators indexed by discrete groups, replacing a large or infinite operator by finite local patches while explicitly accounting for a truncation penalty of order 1/n…
The paper defines an explicit signed-base expansion in which binary digits control both additive contributions and the signs of all later scales. This creates a bounded, non-monotone, self-similar coordinate system whose digit correlations…
The paper develops a transferable mechanism for dynamics approaching a non-hyperbolic degeneracy: induce the map at progressively deeper return scales, separate nearly horizontal branches from transverse branches, and use pressure with…