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 way to preserve convex-order comparisons through Euler-discretized stochastic dynamics. This can transfer to stochastic neural representations or mixture-of-experts by coupling expert states through a…
The paper isolates a scale-critical interaction between fractional diffusion of order 2s and first-order drift, with the rescaled drift coefficient changing as R^{2s-1}. This gives a principled way to make multiscale neural operators…
The paper provides a constructive mechanism for generating many coexisting limit cycles in planar piecewise-linear Lienard systems. Fold points and jump points in the restoring function control the number of cycles, with a construction…
The paper turns least-squares fitting of a matrix into a constrained problem over normal operators, defined by commuting with their adjoint: $A^*A=AA^*$. This suggests a spectral linear layer whose weight is parameterized as…
The paper identifies a structural mismatch in conventional momentum: for a linear layer, each per-example gradient is a key-value outer product, but EMA treats all input directions as if they had identical visitation frequency. Its…
The paper provides a constructive quadratic-manifold reduction framework in which a state is represented by a linear term plus a quadratic Kronecker feature, and projection matrices are chosen to preserve nonlinear moments and the…
The paper proposes the variance of information content as a statistical-complexity measure, C = Var[-log p], which vanishes for both deterministic and equiprobable distributions and is largest in intermediate structured regimes. For…
The paper's transferable asset is not empirical likelihood alone, but the construction of one covariate-balanced probability measure whose every downstream functional automatically preserves distributional shape. This suggests replacing…
The paper constructs a canonical quotient of time-dependent Lie-algebroid paths by identifying paths whose induced local automorphism germ is identical. Its most transferable ingredient is the flow-product law: a noncommutative composition…
The paper provides a constructive class of contact billiard maps whose dynamics on invariant quadratic leaves reduces exactly to iterating a fixed low-dimensional linear transformation. Depending on the quadratic table and leaf parameter…
The paper provides a constructive criterion for state convertibility under a changing reference distribution: a transition matrix must preserve the reference while mapping the target state, and this is equivalent to a martingale coupling…
The paper provides a transferable stability mechanism for graph- or complex-valued neural dynamics: quadratic two-field interactions can exchange energy exactly while contributing zero to the total-energy derivative, provided they are…
The paper derives a non-destructive quantum Jarzynski relation in which nonequilibrium bath drift is quantified by a tunable Renyi divergence rather than only by an ordinary free-energy difference. Its transferable asset is a principled…
The paper identifies the assembly index exactly with the minimum number of productions in a straight-line grammar, turning repeated-substring structure into an explicit optimization target rather than an informal compression heuristic…
The paper identifies the spectral radius of a graph, rather than only its average degree, as the critical scale for Bernoulli edge percolation: the effective transition occurs near p lambda(G) = 1. This gives a principled way to choose…
This paper gives a concrete failure mode for mini-batch stochastic approximation that is stronger than a generic warning about noise: even convex, semialgebraic, piecewise-affine objectives can produce bounded iterates whose accumulation…
The paper identifies a concrete phase structure in diffusion denoising for clustered, heterogeneous low-dimensional data: an early mixing phase followed by a cluster-commitment phase. Its transferable asset is the exact Bayesian…
The paper demonstrates noise-activated switching between coexisting limit cycles, showing that the relevant activation barrier is not a static potential difference but the Freidlin-Wentzell action of the most probable transition path…
The paper provides a coordinate-free method for computing the two quadratic Bogdanov–Takens coefficients from directional derivatives of characteristic-polynomial invariants, avoiding center-manifold construction, Jordan chains, adjoint…
The paper derives an exact, dimension-free envelope for the two competing effects of radial clipping: removed-gradient bias and retained-gradient energy. The transferable asset is the sharp piecewise constant K_p(alpha,beta), together with…
The transferable contribution is a time-domain domain-decomposition strategy for neural differential-equation solvers: replace one long-horizon network by locally trained networks whose initial values are inherited exactly from the…
The paper gives an exact, constructive way to convert a fractional distribution of tree-metric balls into a random finite cover without exceeding a prescribed radius budget. The transferable asset is not graph burning itself, but the…
The paper introduces a composite density-power divergence that robustifies low-dimensional likelihood components without requiring a tractable full joint density. Its transferable asset is an explicit bounded-influence weighting mechanism…
The paper develops a joint factorization of mass on a labelled bipartite graph between parent objects and spatial atoms, rather than independently pruning child and parent selections. Its transferable asset is consistency under refinement…