arXiv research

New CUSUM algorithm detects changes in unnormalized models.

New algorithms detect and react to multiple change points in online learning.

A new index measures how many changes are needed to turn virtual links into simple ones.

New statistical test for change-point detection using relative entropy.

Develops a nonparametric framework for detecting changes in sequential data.

We consider the problem of quickest change-point detection in data streams. Classical change-point detection procedures, such as CUSUM, Shiryaev-Roberts and Posterior Probability statistics, are optimal only if the change-point model is known, which is an unrealistic assumption in typical applied problems. Instead we p…

Defines an implied CO2-price to cover climate change costs, finding it significantly higher than the SCC.

The paper analyzes how stock market dimensionality changes impact portfolio performance.

We study virtual isotopy sequences with classical initial and final diagrams, asking when such a sequence can be changed into a classical isotopy sequence by replacing virtual crossings with classical crossings. An example of a sequence for which no such virtual crossing realization exists is given. A conjecture on con…

Generalized change-point detection using various binary models.

This paper studies a specific metric on plane curves that has the property of being isometric to classical manifold (sphere, complex projective, Stiefel, Grassmann) modulo change of parametrization, each of these classical manifolds being associated to specific qualifications of the space of curves (closed-open, modulo…

Counterexamples to a conjecture on ribbon graph genus changes were found and proven.

In the present paper, we consider local moves on classical and welded diagrams: (self-)crossing change, (self-)virtualization, virtual conjugation, Delta, fused, band-pass and welded band-pass moves. Interrelationship between these moves is discussed and, for each of these move, we provide an algebraic classification. …

A symmetric union of two knots is a classical construction in knot theory which generalizes connected sum, introduced by Kinoshita and Terasaka in the 1950s. We study this construction for the purpose of finding an infinite family of hyperbolic non-fibered three-bridge knots of constant determinant which satisfy the we…

The changing nature of the relationship between a retail bank and its customers is examined, particularly with respect to new financial concepts, debt and regulation. The traditional image of a bank is portrayed as a physical building a classical Doric portico. This image conveys concepts of service, soundness, strengt…

New algorithm detects changes quickly without knowing parameters, near optimally.

New PAC-Bayes bounds derived using Legendre transform and f-divergences.

Paper generalizes paracomposition and change of variables for paradifferential operators.

This paper improves change-point detection for complex data streams using denoising score matching.

New method detects and locates changes in spatio-temporal point processes.

Proposes neural SDEs with change points for better time series modeling.

We consider structural credit modeling in the important special case where the log-leverage ratio of the firm is a time-changed Brownian motion (TCBM) with the time-change taken to be an independent increasing process. Following the approach of Black and Cox, one defines the time of default to be the first passage time…

NN-CUSUM detects changes in high-dimensional data using neural networks.

We consider the problem of change-point detection in multivariate time-series. The multivariate distribution of the observations is supposed to follow a graphical model, whose graph and parameters are affected by abrupt changes throughout time. We demonstrate that it is possible to perform exact Bayesian inference when…

Nearly all field theories suffer from singularities when particles are introduced. This is true in both classical and quantum physics. Classical field singularities result in the notorious self-force problem, where it is unknown how the dynamics of a particle change when the particle interacts with its own (self) field…

Model change points in time-series data with neural SDEs and variational autoencoders.

Dynamic clustering of time series based on volatility shifts.

Cross-validation pitfalls in change-point regression are addressed with new approaches.

We consider flows, called $W^{\rm u}$ flows, whose orbits are the unstable manifolds of a codimension one Anosov flow. Under some regularity assumptions, we give a short proof of the strong mixing property of $W^{\rm u}$ flows and we show that $W^{\rm u}$ flows have purely absolutely continuous spectrum in the orthocom…

Here, a non-linear analysis method is applied rather than classical one to study projective changes of Finsler metrics. More intuitively, a projectively invariant pseudo-distance is introduced and characterized with respect to the Ricci tensor and its covariant derivatives.

Paper proposes a fast method to detect changes in audiometric function.

Singular Yamabe problems involve changing sign solutions with interesting geometric properties.

New algorithm detects and adapts to changes in multi-armed bandit problems.

We show that the Lagrangian of classical mechanics on a Riemannian manifold of bounded geometry carries a periodic solution of motion with rescribed energy, provided the potential satisfies an asymptotic growth condition, changes sign, and the negative set of the potential is non-trivial in the relative homology.

The unknotting number is the classical invariant of a knot. However, its determination is difficult in general. To obtain the unknotting number from definition one has to investigate all possible diagrams of the knot. We tried to show the unknotting number can be obtained from any one diagram of the knot. To do this we…

New method for fast volatility estimation robust to change points.

NEWMA detects changes in multi-dimensional data streams efficiently.

This paper describes a novel approach to change-point detection when the observed high-dimensional data may have missing elements. The performance of classical methods for change-point detection typically scales poorly with the dimensionality of the data, so that a large number of observations are collected after the t…

Forbidden moves categorify fused links into quivers.

Study sharpens unlinking number bounds for special alternating links.

A new robust and flexible classification method for non-Gaussian data.

Detecting the emergence of an abrupt change-point is a classic problem in statistics and machine learning. Kernel-based nonparametric statistics have been used for this task which enjoy fewer assumptions on the distributions than the parametric approach and can handle high-dimensional data. In this paper we focus on th…

In this paper, we introduce two alternative extensions of the classical univariate Value-at-Risk (VaR) in a multivariate setting. The two proposed multivariate VaR are vector-valued measures with the same dimension as the underlying risk portfolio. The lower-orthant VaR is constructed from level sets of multivariate di…

Statistical arbitrageurs have inelastic demand, contrary to classical models.

Proposes training objectives for neural networks to produce robust attributions.

The paper examines how the topology of level sets changes with critical points in Morse theory.

Two virtual link diagrams are homotopic if one may be transformed into the other by a sequence of virtual Reidemeister moves, classical Reidemeister moves, and self crossing changes. We recall the pure virtual braid group. We then describe the set of pure virtual braids that are homotopic to the identity braid.

Survey of various non-classical knot theories from geometric and algebraic perspectives.