2581 valuable arXiv mathematics papers the pipeline has analyzed — each with a short note on what its math gives to machine learning.
The paper gives a constructive reduction of observables in Gaussian random potentials to the joint distribution of local Taylor coefficients, whose covariances are determined by derivatives of the potential Green function. It connects…
The paper's transferable asset is a linearized observability principle: coefficient perturbations are identifiable when their induced state sensitivities cannot remain invisible under a family of time-trace or weighted spatial…
The paper proves a sharp near-optimality guarantee for Lanczos approximations of matrix functions applied to vectors, measured in a matrix-power norm. The transferable asset is an explicit comparison between a short Krylov computation and…
The paper characterizes Lyapunov entropies for nonlinear Fokker–Planck flows through the chemical potential \(\phi(u)+V\), where the diffusion nonlinearity determines the entropy geometry and uniform convexity of \(V\) drives exponential…
The paper turns a fixed quantile level into a state-dependent functional threshold \(\Lambda(x)\), allowing the selected quantile to react differently at different values of the predicted variable. The transferable construction is an…
The paper offers a constructive interval-analysis workflow for certifying the existence, uniqueness, or absence of bifurcation candidates inside a state-parameter box. Its transferable mechanism is the Krawczyk operator applied to…
The paper presents a quantitative chaos-versus-noise diagnostic based on a fixed recurrent reservoir, a trained linear readout, and cross-prediction of future increments. Its transferable mechanism is a restricted dynamical model whose…
The paper gives a constructive bridge between Euclidean monotonicity of a permutation-equivariant vector function on eigenvalues and monotonicity of its orthogonally equivariant spectral lift on symmetric matrices. This is useful for…
The paper offers a constructive interval-analysis workflow for certifying equilibrium existence, exclusion, uniqueness, and outer enclosures uniformly over parameter boxes, rather than relying on sampled parameter values or local solvers…
The paper gives a constructive interpretation of minibatch OT reflow as an alternating projection-like procedure on couplings: reflow replaces a coupling by the deterministic flow induced by its conditional mean velocity, while minibatch…
The paper provides an exact deterministic recursion for second moments of linear systems with i.i.d. multiplicative uncertainty, and proves that mean-square stability is equivalent to Schur stability of a Kronecker-lifted matrix. This…
The paper identifies an actuator singularity: bidirectional-propeller thrust is quadratic in signed rotor speed, so the inverse thrust map has an unbounded derivative at zero thrust. This structure can transfer to neural controllers by…
The paper's transferable contribution is a low-rank latent factor model whose additive reconstruction is replaced by successive Riemannian exponential maps. This gives a principled way to inject anisotropic, curved latent variation into…
The paper provides a mathematically principled template for a history-conditioned constrained response module coupled to an outer dynamical system. Its transferable asset is not the particular stochastic variational inequality application…
The paper provides a control-theoretic route for designing stochastic first-order optimizers rather than selecting momentum and step-size parameters by hand. Its transferable asset is the dynamic integral quadratic constraint (IQC)…
The paper gives an explicit finite family of max-plus invariant features for multisets of points: every basic value is a maximum-weight selection subject to disjointness constraints across feature coordinates. Unlike ordinary sum or mean…
The paper's transferable mechanism is concurrent learning: parameter adaptation uses both current and replayed data, so convergence can be obtained without persistence of excitation. For a scalar unknown decay parameter, one stored sample…
The paper develops a composite adaptive-control construction that estimates an unknown powertrain time constant appearing in the input matrix, while guaranteeing parameter convergence under a much weaker condition than persistent…
The paper provides a constructive online batching framework in which maximum batch delay is controlled by a one-parameter family of nested partitions rather than by request-by-request urgency. The transferable asset is the combination of…
The paper identifies a concrete failure mode of constant-parameter SAM: the perturbation can prevent convergence below a nonzero gradient norm, with a sharp stationarity scale of $(L\rho)^{1/\alpha}$ for the normalized family. The…
The paper presents a constructive complete-abstraction mechanism for monotone control systems: an upper abstraction that supports sound controller refinement and a lower abstraction whose failure certifies infeasibility. Its transferable…
The paper provides a constructive stability principle for residual least-squares training: when the trainable function belongs to a finite-dimensional linearized ReLU space, quasi-uniform deterministic collocation with only linear…
The paper gives a constructive way to build compactly supported partition-of-unity functions whose lattice translates cover every input while a second family of translates is exactly non-overlapping, with a positive geometric buffer after…
The paper offers a constructive persistence mechanism: a Lipschitz bound on certificate evolution is combined with robust contraction of the admissible set to account for sampling and execution latency. This yields a maximal certified…