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 local, covariance-aware stochastic pruning rule for recurrent connections. Instead of ranking weights by magnitude, it estimates how strongly noisy fluctuations at the source and target neurons make a synapse…
The paper provides a constructive way to combine stochastic sample refinement, nonsmooth proximal updates, and Armijo-style backtracking without assuming weak convexity of the regularizer or a uniformly bounded stochastic-oracle variance…
The paper provides an exact label-free objective for neural surrogates of linear finite-element elasticity. Its transferable asset is the identity equating the discrete potential-energy gap with one half of the squared stiffness-norm…
The paper proves a strict sign-truncation principle for the spectral fractional Dirichlet energy: for fractional orders between 1 and 3/2, replacing a sign-changing function u by its absolute value strictly lowers its spectral fractional…
The paper provides a constructive topological mechanism for proving that trajectories follow prescribed itineraries through regions of phase space: h-set covering relations combined with cone invariance and hyperbolic evolution. This can…
The paper gives a sharp, dimension-dependent power-concavity law for Gaussian measure under Minkowski interpolation of convex bodies containing the origin. The transferable asset is not merely the inequality itself, but the explicit…
The paper combines inverse-Laplace contour quadrature with projection-based model-order reduction, yielding a reusable low-dimensional representation for repeatedly evaluating parametric linear dynamics over a time interval. The…
The paper offers a second-order scheduling mechanism: instead of optimizing only average service or throughput, it first assigns each flow a target mean delivery rate and temporal variance, then uses a deficit-based weighted matching…
The paper constructs fuzzy permutation matrices by averaging all order-preserving embeddings of a short permutation into an n by n matrix, then studies linear combinations whose aggregate is exactly constant. The transferable asset is a…
The paper converts dynamical reachability into a geometry by integrating transition probabilities and recording the first time accumulated probability crosses a threshold. The transferable asset is the hitting-time matrix, which detects…
The paper develops a non-equilibrium nucleation theory for bistable reaction-diffusion systems with vector-valued states. Its transferable mechanism is that deterministic front speed acts like a bulk driving force, while an effective…
The paper gives a constructive persistence mechanism for analytic invariant graphs carrying rigid irrational rotations under Gevrey perturbations of twist maps. Its transferable asset is a parameterized direct KAM correction scheme that…
The paper develops port-Hamiltonian interconnections for nonlinear rigid and flexible subsystems using state-dependent Dirac structures. Its transferable mechanism is exact internal power cancellation: subsystem Hamiltonians add, while…
The paper identifies gauge equivariance as the mathematical condition separating optimizers that preserve the implicit low-rank behavior of factored models from coordinate-wise methods that destroy it. For a factorization W=UV^\top, the…
The paper provides an operator-level recipe for separating macroscopic and microscopic behavior without relying on coordinates, spatial stationarity, or a Brillouin zone. Its transferable asset is the combination of accretive…
The paper supplies a concrete mixed discrete-continuous chain complex: a singular chain, a current encoding continuous geometric mass, and an integral-current curvature are coupled by an exact boundary operator. This structure is…
The paper provides a constructive way to solve model-free reachability reinforcement learning despite the fact that the undiscounted Bellman operator is noncontractive and its fixed-point equation has multiple solutions. Its key mechanism…
The paper provides a constructive way to turn a diffusion with a known target density into an exact path-space rejection sampler, using Girsanov density ratios and unbiased estimators that require only a constant number of…
The paper provides a constructive method for converting non-Markovian temporal specifications into Markovian control by augmenting each environment state with deterministic automaton states. Its most transferable mechanism is an…
The paper gives an exact density criterion for time-frequency systems generated by continuous integrable totally positive windows: the Gabor atoms form a complete stable frame precisely when the time-frequency cell satisfies…
The paper turns information-dependent equilibrium constraints into positive-semidefinite operator inequalities, making the feasible equilibrium set a compact spectrahedron rather than an implicitly defined set of policies. This is…
The paper supplies a sharp, dimension-aware continuity modulus for optimized Rényi conditional entropy under trace-distance perturbations. Its transferable asset is not the quantum formalism itself, but the explicit worst-case entropy…
The paper combines a positive-domain Gamma-noise fidelity with an explicit geometric regularizer involving surface area and mean curvature, then minimizes the resulting nonconvex objective by mirror descent inside a deep-equilibrium…
The paper provides a constructive space–time Onsager framework in which transport is represented by lagged, spatially resolved response kernels rather than a single instantaneous coefficient. Its transferable asset is the hierarchy from…