2581 valuable arXiv mathematics papers the pipeline has analyzed — each with a short note on what its math gives to machine learning.
The paper's transferable contribution is a co-design principle: choose the feedback or preconditioning matrix and the event-trigger threshold jointly under a robust Lyapunov certificate, rather than selecting an optimizer first and adding…
The paper introduces a direction-dependent subgaussian geometry for a convex body: each projection is scored by the ratio between its ψ2-norm and its L2-norm. This suggests a neural-network regularizer that controls heavy-tailed feature…
The paper develops a Hall-type feasibility theory for selecting pairwise disjoint representatives from hypergraphs whose resource supports are subtrees of an index tree. The transferable asset is a structured, globally collision-free…
The paper develops data-driven feedback-stabilization conditions that certify a controller against an entire uncertainty set of plants consistent with noisy measurements, rather than only against a fitted model. The transferable asset is…
The paper provides a sharp, distribution-free way to quantify apparent reversals in trajectory distributions using log-likelihood ratios rather than arbitrary scalar observables. Its transferable asset is the separation between a physical…
The paper reduces real-time sliding-window decoding to a coarse-grained parity-conserving reaction-diffusion process: charged defects diffuse, annihilate in pairs, and nucleate in pairs. The transferable asset is not the…
The paper provides a generalized master-stability mechanism for synchronization of directed, weighted, degree-heterogeneous networks with coupling delays. Its transferable asset is that stability is determined jointly by a delay-dependent…
The paper contains a useful online uncertainty-calibration mechanism rather than merely a robotics-specific controller. Its adaptive conformal inference update maintains several horizon-specific error radii and increases a radius whenever…
The paper gives a constructive characterization of which subsets of a finite distributive lattice can be made exactly optimal by a modular score. Under Birkhoff's representation, every lattice element becomes a down-set of…
The paper gives a quantitative way to design and assess minimax polynomials when the admissible spectral set is disconnected or contains isolated, irregular points. The transferable asset is the separation between the dominant capacity…
The paper proves a logarithmic-free high-moment inequality for sums of weakly interacting functions of independent examples. Its transferable asset is the explicit separation between cross-example sensitivity beta and single-example…
The paper gives an exact bridge between a constrained two-vector numerical range and all numerical ranges obtained by similarity transforms whose condition number is bounded. This is directly relevant to nonnormal neural dynamics: ordinary…
The paper provides a mathematically grounded explanation for why small-noise stochastic optimization can prefer singular, highly overparameterized solutions rather than generic zero-loss solutions. Its transferable asset is the…
The paper provides a constructive Følner–paradoxical dichotomy for étale groupoids: fiberwise amenability supplies finite sets whose compact-neighborhood growth is arbitrarily close to one, while non-amenability supplies many disjoint…
The paper exposes a deterministic covariance iteration hidden inside thermodynamic matrix inversion: an Ornstein–Uhlenbeck discretization updates a matrix by two-sided contraction plus isotropic injection, and its fixed point is the…
The paper provides a concrete discrete-time mechanism for emergent oscillation: a consensus equilibrium loses stability when a real mode crosses the multiplier -1, producing a supercritical flip bifurcation and a stable period-two orbit…
The paper provides a transferable mechanism for recovering sparse dynamical couplings from partial state observations: passive trajectories may be structurally non-identifying, whereas controlled perturbations can make the interaction…
The paper’s main transferable asset is not a new activation but the deliberate enforcement of input convexity, which turns a neural surrogate into an object with exploitable global geometry. Nonnegative hidden-to-hidden weights preserve…
The paper provides a precise entropy-amplification mechanism under the probability-measure lift of a dynamical system: a compact state set with positive upper-capacity entropy induces infinite upper-capacity entropy on the space of all…
The paper supplies a constructive stability diagnostic for iterated linear dynamics: instead of requiring every power of an operator to remain bounded, it controls the density of time indices at which orbit norms exceed a threshold. The…
The paper provides a useful control formulation for decentralized continual learning: agents repeatedly apply a fixed number of consensus and gradient steps while the target objective changes as new samples arrive. The transferable asset…
The paper gives a constructive separation between stored weights and task behavior: a frozen, randomly initialized single-layer softmax transformer can implement a kernel regressor when its prompt is chosen by solving linear systems. The…
The paper offers a transferable hierarchical control mechanism rather than a generic optimizer: an upper phase/energy loop generates a near-optimal, hard-motion-constrained velocity reference, while a lower feedback loop tracks that…
The paper provides an explicit randomized representation of elliptic solutions in terms of Brownian exit times, boundary evaluations, and accumulated source terms, together with a Walk-on-Spheres discretization whose error can be…