arXiv research

New definition resolves ambiguity in non-stationary bandit classification.

The method approximates stationary distributions of Markov models by truncating irrelevant states.

Proposes a new algorithm for non-stationary bandits.

The paper classifies ruled surfaces in Lorentz-Minkowski space that are stationary for the moment of inertia.

SmoothFBO tackles non-stationary functional bilevel optimization.

A Hamiltonian stationary Lagrangian submanifold of a Kaehler manifold is a Lagrangian submanifold whose volume is stationary under Hamiltonian variations. We find a sufficient condition on the curvature of a Kaehler manifold of real dimension four that guarantees the existence of a family of small Hamiltonian stationar…

Proposes a method to forecast non-stationary time series.

The paper simplifies arguments for stationary varifolds results.

This is the second part of the investigation started in [Stationary solutions and asymptotic flatness I]. We prove here that Strongly Stationary ends having cubic volume growth are Weakly Asymptotically Flat. Combined with the results of the previous paper this shows that Strongly Stationary ends are Asymptotically Fla…

The paper improves energy decay estimates for Dir-stationary Q-valued functions and applies them to Liouville-type theorems and continuity.

Study on fake stationary Volterra Heston model for non-stationary processes.

We study surfaces in TN that are area-stationary with respect to a neutral Kaehler metric constructed on TN from a riemannian metric g on N. We show that holomorphic curves in TN are area-stationary, while lagrangian surfaces that are area-stationary are also holomorphic and hence totally null. However, in general, are…

Two classification results for stationary surfaces of least moment of inertia.

Algorithm minimizes regret in non-stationary dueling bandits with unknown parameters.

The paper establishes a connection between minimal surfaces and a family of stationary surfaces via inversions.

Study geometric flow on curves with positive torsion, finding stationary solutions and their stability.

We develop a general method of proving the ellipticity of boundary value problems for the stationary vacuum space time, by showing that the stationary vacuum field equations are elliptic subjected to a geometrically natural collection of boundary conditions in the projection formalism. Using this we prove the manifold …

It is demonstrated that the stationary Veselov-Novikov (VN) and the stationary modified Veselov-Novikov (mVN) equations describe one and the same class of surfaces in projective differential geometry: the so-called isothermally asymptotic surfaces, examples of which include arbitrary quadrics and cubics, quartics of Ku…

DAL enhances black-box bandit algorithms for non-stationary environments.

The paper studies Gauss maps of space-like stationary surfaces in Lorentz-Minkowski space, focusing on ramification and unicity.

We study the classification of area-stationary and stable $C^2$ regular surfaces in the space of the rigid motions of the Minkowski plane E(1,1), equipped with its sub-Riemannian structure. We construct examples of area-stationary surfaces that are not foliated by sub-Riemannian geodesics. We also prove that there exis…

The study finds conditions for free boundary Hamiltonian stationary discs in complex 2-space.

Flexible GP model improves wind power prediction accuracy.

Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.

Study incentivizes exploration in non-stationary MAB with compensation.

Study axisymmetric surfaces in Euclidean space for energy minimization.

New algorithm tackles non-stationary reinforcement learning with general function approximation.

Extends geometric approach to model non-stationary extremal dependence.

The problem of time-series clustering is considered in the case where each data-point is a sample generated by a piecewise stationary ergodic process. Stationary processes are perhaps the most general class of processes considered in non-parametric statistics and allow for arbitrary long-range dependence between variab…

New definitions of ESP for quantum reservoir computing handle non-stationary systems.

Study combines VICReg and TNC for better encoding of non-stationary seismic signals.

We propose non-stationary spectral kernels for Gaussian process regression. We propose to model the spectral density of a non-stationary kernel function as a mixture of input-dependent Gaussian process frequency density surfaces. We solve the generalised Fourier transform with such a model, and present a family of non-…

A contact stationary Legendrian submanifold of $S^{2n+1}$ is a Legendrian submanifold whose volume is stationary under contact deformations. The simplest contact stationary Legendrian submanifold (actually minimal and Legendrian) is the real, equatorial $n$-sphere $S_0$. This paper develops a method for constructing co…

New findings show Bregman proximal algorithms can get stuck near non-stationary points.

New algorithm tackles non-stationary delayed feedback in recommender systems.

Polyconvex energies with conformal invariance have smooth stationary points outside a discrete set.

The paper proves that certain stationary hypersurfaces in high dimensions are essentially flat.

Stationary measures on hyperbolic surfaces with cusps are singular and stable under quasi-symmetries.

The paper proves smoothness of stationary varifolds.

Algorithm adapts to non-stationary rewards without prior knowledge.

The paper provides exact multivariate amplitude distributions for non-stationary Gaussian or algebraic fluctuations.

Study shows singular set of certain graphs has codimension 1.

Smooth solutions found for Hamiltonian stationary equations in low dimensions.

Kernel-based tests detect dependencies in multivariate time series, including stationary and non-stationary data.

Study finds conditions for stationary spacelike surfaces in a generalized Robertson-Walker spacetime.

This paper develops the first method for the exact simulation of reflected Brownian motion (RBM) with non-stationary drift and infinitesimal variance. The running time of generating exact samples of non-stationary RBM at any time $t$ is uniformly bounded by $\mathcal{O}(1/\barγ^2)$ where $\barγ$ is the average drift of…

New method reduces computational cost for learning stationary diffusions.

Predictive sampling improves on Thompson sampling for non-stationary bandit environments.