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 continuous, noncommutative interpolation between standard Petz and maximal quantum f-divergences through an affine-invariant geodesic of relative modular operators. This is transferable to neural models whose…
The paper gives explicit, uniform estimates for how many eigenmodes of a time-frequency concentration operator remain above a prescribed energy threshold, including the logarithmic-width transition region around the Shannon number. This is…
The paper identifies a rigid information-geometric structure for probability simplices: under the square-root map, the Fisher–Rao metric becomes the Euclidean metric on a sphere, and the reset-neutral separatrix becomes a totally…
The paper supplies an explicit orthogonal decomposition of differential forms on a torus into harmonic, exact, and co-exact components, with each component carrying different global or local structure. This is transferable to neural ODEs…
The paper provides a constructive prescribed-performance observer (PPO) whose nonlinear, dynamically scaled gains estimate unmeasured tracking-error derivatives from only the output error while enforcing a quantitative transient envelope…
The paper gives a constructive structural theorem for sparse graphs: every graph of arboricity k can be partitioned into a k-degenerate backbone and a residual graph of maximum degree at most k-1, with the more general feasibility…
The paper develops a constructive mechanism for counting isolated periodic solutions of generalized Abel equations with coefficients drawn from Chebyshev families. Its transferable asset is a zero-count certificate: a nonzero linear…
The paper's main transferable asset is a constructive, computer-assisted method for certifying local bifurcation structure in an infinite-dimensional nonlinear system. For neural networks, the closest target is an implicit layer, neural…
The paper gives a constructive controllability principle: on a compact manifold, horizontal vector fields can be represented by a uniformly bounded number of Lie brackets of horizontal gradient fields, with bracket depth controlled by the…
The transferable contribution is an exact reduced-space treatment of large equality-constrained discretized dynamics, combined with a projected primal-dual gradient kernel whose cost is dominated by fixed-size matrix-vector products rather…
The paper identifies a non-extensive error-control principle for truncating long-range interactions: local observables are governed by the discarded interaction mass incident on each site, not by the global norm of all discarded terms. For…
The paper provides a constructive blocking and cylinder-set approximation mechanism showing that highly irregular indicator observables can still satisfy strong statistical limit laws in slowly, polynomially mixing hyperbolic systems. Its…
The paper provides a constructive boundary-to-volume parametrization whose Jacobian separates geometry from a universal radial factor \(\rho^{d-1}\). This can become a deterministic integration layer for neural fields, PINNs, and geometric…
The paper studies a dimension-free inequality for aggregating matrix summands, comparing the Schatten norm of a signed sum with the Schatten norm of the sum of positive operators |A_k|. The transferable asset is a principled budget for…
The paper gives an explicit calculus for how several simultaneous boundary singularities combine: product interactions add active exponents, while sum interactions are controlled by the largest exponent. The resulting finite-distance…
The paper studies the convex cone of symmetric matrices whose every d-by-d principal submatrix is positive semidefinite, a hierarchy that is cheaper to enforce than global positive semidefiniteness. The transferable asset is the explicit…
The paper's transferable mechanism is quasi-analytic rigidity: for analytic twist maps, Mather's beta function has a highly regular extension, so equality on a positive-measure subset of KAM rotation numbers forces equality on all…
The paper offers a constructive dynamic realization that preserves asymmetric actuator limits by embedding the constraint directly into the vector field instead of applying post-hoc clipping. Its transferable mechanism is a bounded state…
The paper offers a transferable model-free safety mechanism: estimate an ultra-local input-output dynamics model online, quantify its prediction error with an uncertainty envelope, and insert that envelope directly into a robust…
The paper offers a transferable constrained-policy mechanism combining three components: per-timestep group normalization, trajectory-level ranking by terminal feasibility, and a projected adaptive dual variable. The useful asset is not…
The paper identifies an exact second-moment defect: the gap between the squared norm of the conjugate degree partition and the squared norm of the nonzero up-Laplacian spectrum equals twice the number of failed elementary shifts. Its…
The paper provides a truncated commutative algebra whose coefficient propagation computes arbitrary-order repeated directional derivatives without materializing derivative tensors. Its most transferable asset is the combination of…
The paper's transferable asset is a design-aware control-variate construction: instead of choosing a baseline heuristically, it selects basis directions that optimally explain covariance induced by sampling or exposure mechanisms and…
The paper's transferable asset is an exact, derivative-free pseudo-linearization of nonlinear dynamics, followed by repeated solution of structured linear-quadratic subproblems. Rather than differentiating a learned world model through a…