2581 valuable arXiv mathematics papers the pipeline has analyzed — each with a short note on what its math gives to machine learning.
The paper develops a Schur-Agler realization for the hexablock: bounded holomorphic functions are represented through a block-diagonal contractive multiplier and an auxiliary Hilbert-space feature map. The key transferable asset is the…
The paper provides a transferable persistence mechanism: an attracting weakly normally hyperbolic invariant torus survives sufficiently small time-periodic perturbations, and averaging converts an attracting torus of an averaged autonomous…
The paper provides an ordered factorization of a nonnegative banded transition matrix into positive bidiagonal factors, with the factor order retaining structure that is hidden in the multiplied matrix. This gives a cheap…
The paper isolates a useful asymmetry in quadratic optimal transport: under strong convexity and regularity, a potential can be controlled in an invariant L1 norm by a weak discrepancy between the distributions induced by its gradient…
The paper combines a differentiable soft minimum over a finite set of valid configurations with a safety-filtered feedback controller, giving a useful pattern for neural policies: represent successful behaviors as configuration prototypes…
The paper provides a concrete spectral representation of a quaternary symmetric noise channel: a Hadamard transform diagonalizes the channel, turning symbol substitutions into independent coordinate contractions whose strengths are powers…
The paper offers a concrete hierarchical objective: each layer pays a Gaussian KL cost for disagreement between its top-down prediction and the lower-layer representation, with the disagreement weighted by learned precision. This creates a…
The paper offers a constructive mechanism for learning partially observed dynamics: separate measured-coordinate physics from a hidden-state coupling residual, fit that residual, project it onto a constrained symbolic library, and admit…
The paper identifies a sharp propagation law for activation cascades driven by translation-invariant heavy-tailed jumps: when the tail exponent satisfies $0<\alpha<d$, a distance-$L$ region can be activated in only $(\log L)^{\Delta+o(1)}$…
The paper provides a constructive countable-branch iterated-function-system mechanism: uniformly contracting inverse branches encode trajectories by sequences over a countably infinite alphabet, while the induced expanding map is conjugate…
The paper's transferable asset is a structure-preserving low-rank evolution: compression is not allowed to discard directions representing conserved moments, and stochastic integration is chosen to respect the geometry of the original…
The paper offers a constructive sparse symbolic-regression mechanism: represent a target as a linear combination of candidate nonlinear basis functions while jointly learning both their coefficients and structural parameters such as…
The paper provides a transferable robustness mechanism: for stochastic flows, measure-theoretic entropy is related to exponential volume growth along stable submanifolds, and under an integrability condition entropy is upper semicontinuous…
The paper provides a transferable mechanism for combining non-Markovian memory with a time-antisymmetric rotational coupling. Eliminating a slow bath variable produces a non-reciprocal memory kernel whose orientation rotates in time, while…
The paper provides a constructive extinction-versus-persistence mechanism for a deterministic graph cellular automaton with healthy, infected, and dead states. Its most transferable result is the characterization of exact period-two…
The paper constructs a finite-bin bridge from independent microscopic spike events to mesoscopic population-rate dynamics, yielding both an explicit conditional noise law and covariance evolution controlled by a small Jacobian. The…
The paper introduces a nonlinear perturbation of finite Markov dynamics in which transition coefficients depend quadratically on inner products of probability vectors. The transferable asset is a simplex-preserving nonlinear operator: the…
The paper identifies a minimal mechanism for habituation: a nonlinear static input-output transformation driven by a linear fading-memory state. Its key negative result is that a linear time-invariant system cannot satisfy both response…
The paper provides a practical way to differentiate through a converged constrained optimization solver without storing its entire trajectory. Its key asset is the separation between the full forward solve and a short backward trace…
The paper offers a transferable system-identification mechanism: construct a physics-constrained sparse library, fit its coefficients robustly with total least squares and random-sample consensus, and use the resulting model inside a…
The paper constructs a reproducible source of structured complex randomness by assigning independent unit-circle phases to primes and extending them completely multiplicatively, then shows that periodic modulation behaves asymptotically…
The paper identifies a nonstandard feasible body for categorical distributions that is preserved when independent random variables are combined by group or quasigroup convolution. The transferable asset is a compositional guarantee…
This paper provides a concrete way to learn dataset-adaptive orthogonal or unitary transforms without sacrificing exact invertibility, norm preservation, or near-linear application cost. The transferable asset is the parameterization: a…
The paper separates path selection into a time-antisymmetric entropy term and a time-symmetric dynamical-activity (frenesy) term, then constructs cases where the entropy contribution is exactly zero and all selection comes from local…