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 macroscopic-fluctuation-theory description of multi-time current fluctuations in non-stationary diffusive systems. Its transferable asset is a path-space action, together with perturbative multi-time…
The paper contributes a design-based way to distinguish predictive fit from informational sufficiency: commit the endpoint using only past information, then randomise a later exogenous variable that could not have influenced that…
The paper provides a constructive coarse-to-fine strategy for solving enormous nonnegative transport problems without materializing the full variable set: initialize a sparse active support from a coarser solution, refine it, and…
The paper contributes a constructive mechanism for moving between network topologies without violating feasibility during the transition: a receding-horizon planner proposes a sequence, while a higher-fidelity feasibility filter rejects…
The paper's transferable contribution is a mode-preserving alternative to global randomized smoothing for stochastic predictors. Instead of averaging all noisy predictions, it partitions prediction samples into clusters and applies…
The paper offers a constructive quantized distributed-control mechanism: a passivity-based iteration is combined with time-varying scaling of an ultimate-boundedness quantization error, allowing geometric convergence despite low-bit…
The paper supplies structured, non-learned triangular transforms whose coefficients obey simple recurrences and whose repeated binomial transform has an explicit closed form. This can be transferred into sequence models as an invertible…
The paper gives a constructive Perron-type variational description of the principal eigenvalue for irreducible asymmetric nearest-neighbor operators, expressed through positive profiles and periodic logarithmic correctors. The transferable…
The paper provides a concrete radial-filtration construction for extracting extended topological structure from Euclidean shapes, together with a reduction from a manifold to its boundary and a certified discretization error bound. The…
The paper constructs a Bellman propagation operator whose coefficients are nonnegative because each update is represented as a conditional expectation over reflected weak-Euler branches. The transferable asset is a monotone…
The paper identifies an algebraic mechanism controlling whether self-similar Delone patterns remain uniformly discrete: under its stated mild hypotheses, the similarity factor is Pisot exactly when uniform discreteness holds. A Pisot…
The paper supplies a hardware-oriented replacement for query-key dot products in spiking attention: compare first-spike latency vectors with an l1 metric and convert the distance into a Laplacian affinity. This is more than a generic…
The paper turns conditioning of a Weyl–Heisenberg measurement frame into an explicit max–min problem over ambiguity intensities: the nonidentity Gram eigenvalues are exactly d times the squared magnitudes of the fiducial's displacement…
The paper's most transferable asset is its separation of observation, finite-dimensional representation, operator prediction, and reconstruction, together with explicit control of measurement error. This suggests neural operators whose…
The paper supplies a sharp reverse inequality: a Riesz potential cannot have arbitrarily small output norm relative to the input mass and sub-unit L^q quasi-norm. This is useful as an anti-collapse certificate for nonnegative feature…
The paper combines Koopman-generator identification with geometric solution of Hamilton-Jacobi-Bellman equations, offering a structured way to learn controlled dynamics and value functions from trajectories. The transferable asset is the…
The paper provides a transferable spectral mechanism for normalized projective dynamics: after repeated application of a projectivity and area/barycenter normalization, asymptotic geometry is determined by dominant eigenvalues. A unique…
The paper's transferable contribution is a certified greedy refinement rule: compare candidate function blocks only after projecting out what the current representation already explains, then reject unstable directions and rank the…
The paper identifies a computable local contraction factor for Sinkhorn-Knopp scaling that is much sharper than worst-case global bounds. For target row marginal p and column marginal q, the rate is governed by the second-largest…
The paper provides a concrete identifiability mechanism for model-free output-feedback control: a dynamic input-output filter can produce a lifted vector with many deterministic redundant directions, even though only 2n components in SIMO…
The paper supplies a quotient-space viewpoint for relational data: measurable Z-valued kernels are identified under measure-preserving reparameterizations, and the quotient map onto Z-Gromov-Wasserstein space is a submetry. This means…
The paper provides a constructive dilation of a generally non-skew Koopman generator into a skew-adjoint operator on an enlarged Hilbert space. Writing the generator as V=S+A, with S=(V+V*)/2 self-adjoint and A=(V-V*)/2 skew-adjoint, it…
The paper turns spherical design exactness into a deterministic, highly isotropic directional discretization: equal-weight nodes reproduce every spherical polynomial up to degree t, while their Minkowski polytope has surface-area measure…
The paper offers a nonstandard asymptotic mechanism for sampled-action Bellman operators: near-optimal candidates form a marked Poisson point process after rescaling, and the leading value error is determined by a nonlinear tangential…