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 explicit homotopy-preserving reduction rules for independence complexes: when one vertex has a neighborhood contained in another's, the dominated vertex can be removed without changing the complex up to homotopy. It also…
The paper provides a constructive way to turn scalar tensor-product wavelets into vector-valued bases whose basis elements mix signal components rather than processing channels independently. The transferable asset is a fixed, perfectly…
The paper's key transferable mechanism is that stealthy controller-parameter tampering can preserve apparent stability while changing equilibrium points and reducing dynamic margins. Its modified PLL deliberately makes a hidden gain…
The paper turns exclusion of simultaneous zeros of two quadratic forms into a constructive positive-definite pencil certificate: for n >= 3, two homogeneous equations have no common nonzero solution exactly when some nontrivial linear…
The paper provides a general way to turn covering-number growth into a probability measure whose mass is exponentially small in every sufficiently small metric ball. This suggests a representation-learning regularizer: instead of merely…
The paper proves a sharp, dimension-free sup-norm bound for a carefully normalized Jacobi-polynomial feature, together with decay guarantees for a related discrete Laguerre evolution. The transferable asset is the normalization that makes…
The paper turns a nonsmooth positive-part contact law into the exact central-path map \(\varphi_{+,s}(w)=\frac{w+\sqrt{w^2+4s}}{2}\), obtained by eliminating a strictly positive slack variable under a logarithmic barrier. Its transferable…
The paper provides a transferable mechanism for stabilizing coupled nonlinear systems when control events are detected at one time but executed after an actuation delay. Its main assets are a delay-dependent Lyapunov contraction condition…
The paper provides a simple, hardware-relevant sparsification operator rather than merely pruning weights: it removes low-magnitude activation events while retaining both positive and negative outliers. The transferable asset is the…
The paper provides a transferable robust-control interpretation of algorithmic stability: replacing one training sample is treated as an exogenous disturbance entering a sensitivity system, while the incremental behavior of the…
The paper’s transferable asset is not a new preconditioner, but a non-asymptotic analysis showing that RMSprop’s optimization error can be controlled uniformly as the regularization parameter epsilon approaches zero and as the…
The paper supplies a distribution-free, rank-based independence certificate that remains valid for arbitrary real-valued bivariate laws, including ties, mixed distributions, and singular support. Its key transferable asset is the…
The paper supplies highly symmetric sparse graphs obtained from switching classes of regular two-graphs, with exact strongly regular parameters controlling every pairwise common-neighbor count. This uniformity is transferable to sparse…
The paper provides a constructive converse mechanism: for a continuous stochastic discrete-time system, a uniform strict reach-avoid probability margin over a compact initial set implies the existence of a barrier-like certificate…
The paper proves a sharp, degree- and parameter-sensitive envelope for weighted orthonormal Jacobi polynomials, including the non-removable intermediate growth factor S^{1/3}. This can be transferred to neural networks as a principled…
The paper's transferable contribution is a decentralized online optimizer that keeps each worker's communication state in dual space, rather than repeatedly exchanging model parameters or full historical gradients. Barrier-FTRL combines…
The paper gives a precise way to make additive subspace corrections robust when several positive-semidefinite penalties have independently varying weights. The transferable asset is not the finite-element application itself, but the…
The paper provides a transferable identification mechanism for discovering differential and algebraic structure directly from noisy multivariate trajectories, without assuming which channels are inputs or outputs or knowing the DAE index…
The paper gives a sharp structural result for compressing multi-output linear regression datasets: exact recovery of the minimum-Frobenius-norm empirical-risk minimizer is possible with at most (m+1)r weighted examples, where r is the…
The paper provides a transferable recipe for constructing recurrent linear operators whose powers remain uniformly bounded despite non-normal ordering of transport and relaxation. Its key ingredients are an equilibrium-metric unitary…
The paper supplies a concrete manifold of subspaces whose intrinsic bilinear form has a prescribed mixed signature, represented using ordinary Euclidean projectors and a fixed indefinite metric. This gives neural modules a controlled way…
The paper treats recurrent motifs as finite transformation systems and studies the monoid generated by input-conditioned state updates, rather than analyzing each update in isolation. Its transferable asset is a constructive way to design…
The paper gives a sharper high-dimensional Gaussian approximation for maxima of sums of independent, coordinatewise subexponential variables under completely unrestricted covariance, improving the dominant rate from roughly n^{-1/4} to…
The paper offers a nontrivial robust-control mechanism: structured singular-value (μ) synthesis designs a dynamic controller that remains performant under simultaneous, structured model uncertainties, followed by balanced-truncation…