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 realize every conditional-probability matrix as a Born-rule measurement, and to realize it as a marginal of a higher-dimensional unitary transition. The transferable asset is not the POVM notation…
The paper gives a constructive way to obtain geometric convergence without projections or linear-optimization oracles when the feasible set has a rolling-ball smoothness condition. Its transferable asset is an approximate local linear…
The paper provides a nonstandard, observable-specific order condition for Runge-Kutta discretizations of fast-slow systems: although two independent third-order defects appear locally for any second-order method, fold passage annihilates…
The paper's transferable asset is a radial diffeomorphism that converts an unbounded heavy-tailed distribution into a distribution on a bounded Euclidean ball while explicitly accounting for volume distortion through the Jacobian. This can…
The paper derives an explicit second-moment recursion for stochastic momentum under a one-point convexity condition that controls both distance to a target and population-gradient magnitude. Its transferable asset is the decomposition of…
The transferable asset is the use of a low-dimensional invariant manifold whose chart and internal dynamics obey the same group action as the full system. This provides a principled way to build latent neural ODEs or state-space models…
The paper constructs a canonical trace-free Beurling--Ahlfors transform on differential forms by combining complementary Hodge projections with coefficients chosen to cancel the channel trace. Its useful transferable asset is not the…
The paper provides a practical mechanism for differentiating through affine-parametric quadratic programs without repeatedly differentiating a full generic optimization graph. Its most transferable assets are active-set reduction of the…
The paper provides a constructive feedback-synthesis mechanism based on lifting a controlled system to a Hamiltonian flow and representing the optimal feedback as an invariant stable manifold. The key transferable asset is the geometric…
The paper shows that high-dimensional correlation matrices can be entrywise close to the identity while being globally far from it, having a Marchenko–Pastur-like spectrum, and possessing an extremely small minimum eigenvalue. This…
The paper turns support-constrained coupling into a graph-theoretic feasibility problem: a binary support pattern can carry prescribed marginals exactly when every subset satisfies a Hall-type neighborhood inequality. This gives a concrete…
The paper identifies a structural reduction for binary optimization: maximizing the norm of a signed vector sum does not require searching all 2^N sign patterns. Any global optimizer is generated by thresholding vector projections onto one…
The paper provides a constructive mechanism for making the period of stable oscillations locally insensitive to an input. Near a nondegenerate Hopf bifurcation, Lyapunov-Schmidt reduction produces a low-dimensional amplitude-phase system…
The paper gives a recursive representation of matrices whose row and column index trees have complementary low-rank blocks. Its transferable asset is not merely low rank, but a multiscale factorization in which block-diagonal orthonormal…
The paper's transferable mechanism is intrinsic stochastic successive convexification on a Lie group: represent pose increments in the se(3) tangent algebra, retract them through the exponential map, and optimize nominal motion…
The paper recasts KV-cache compression as attention-product distortion rather than ordinary entrywise reconstruction error. Its most directly transferable construction is a volume-aware partition of transformed coefficients: equal-volume…
The paper gives a constructive way to turn a collection of positive semidefinite class states into a normalized measurement, using one unconstrained Hermitian matrix rather than directly optimizing all measurement operators. The key…
The paper provides a constructive recurrent parameterization in which each two-dimensional mode has an exactly controlled rotation angle and decay rate, rather than using an unconstrained random recurrent matrix followed by spectral-radius…
The paper gives a constructive mechanism by which inverse-gamma fluctuations of total kinetic energy generate kappa-distributed single-particle velocities in the large-particle limit. The transferable asset is an analytically controlled…
The paper's transferable contribution is a modular robust chance-constraint interface: uncertainty is converted into reliability-indexed resource reservations, while the downstream optimizer remains agnostic to how those reservations were…
The paper gives a quantitative anti-concentration principle for two-dimensional polynomial maps of independent random inputs: if the highest-degree components of the two outputs are not proportional, the joint law cannot place excessive…
The paper's transferable asset is a finite-horizon alternative to confidence sequences: instead of protecting against infinitely many future peeks, it allocates error only across a predeclared maximum of H monitoring times. This yields…
The paper proves Crouzeix's functional-calculus inequality: evaluating any polynomial on a possibly highly non-normal operator is controlled, up to a factor of 2, by the polynomial's maximum over the operator's numerical range. This is…
The paper provides a constructive hybrid-control mechanism combining a single-state reset controller with an integral sliding-mode controller (ISMC). Its key transferable asset is decoupling: reachability of the sliding surface is made…