arXiv research

Analyzes Kodaira-Iitaka dimension and multiplicity using intersection theory.

Proposes a neural network for handling multi-sensor time series with varying input dimensions.

A new stable similarity measure for time series using persistent homology.

Forecasting high-dimensional time series plays a crucial role in many applications such as demand forecasting and financial predictions. Modern datasets can have millions of correlated time-series that evolve together, i.e they are extremely high dimensional (one dimension for each individual time-series). There is a n…

In this paper, we study Basmajian-type series identities on holomorphic families of Cantor sets associated to one-dimensional complex dynamical systems. We show that the series is absolutely summable if and only if the Hausdorff dimension of the Cantor set is strictly less than one. Throughout the domain of convergence…

Sentinel improves time series forecasting by modeling both temporal and channel dependencies.

We give a computer free proof of the Deligne, Cohen and deMan formulas for the dimensions of the irreducible $g$-modules appearing in the tensor powers of $g$, where $g$ ranges over the exceptional complex simple Lie algebras. We give additional dimension formulas for the exceptional series, as well as uniform dimensio…

CaLoNet integrates spatial and local correlations for multivariate time series classification.

New method preserves distances in time series data.

We propose a new variational Bayes estimator for high-dimensional copulas with discrete, or a combination of discrete and continuous, margins. The method is based on a variational approximation to a tractable augmented posterior, and is faster than previous likelihood-based approaches. We use it to estimate drawable vi…

We provide the proof that the space of time series data is a Kolmogorov space with $T_{0}$-separation axiom using the loop space of time series data. In our approach we define a cyclic coordinate of intrinsic time scale of time series data after empirical mode decomposition. A spinor field of time series data comes fro…

Classifies almost-toric systems in four dimensions.

Introduces a new benchmark for time series extrinsic regression.

Invariants measure letter interleaving in groups, detecting group dimensions.

We propose a graph spectral representation of time series data that 1) is parsimoniously encoded to user-demanded resolution; 2) is unsupervised and performant in data-constrained scenarios; 3) captures event and event-transition structure within the time series; and 4) has near-linear computational complexity in both …

Geodesics with bounded angles have zero Hausdorff dimension.

Symbolic LSTM improves time series forecasting by reducing hyperparameter sensitivity.

Aimed at geometric applications, we prove the homology cobordism invariance of the $L^2$-betti numbers and $L^2$-signature defects associated to the class of amenable groups lying in Strebel's class $D(R)$, which includes some interesting infinite/finitenon-torsion-free groups. The proofs include the only prior known c…

We determine all connected homogeneous Kobayashi-hyperbolic manifolds of dimension $n\ge 4$ whose group of holomorphic automorphisms has dimension either $n^2-4$, or $n^2-5$, or $n^2-6$. This paper continues a series of articles that achieve classifications for automorphism group dimension $n^2-3$ and greater.

GGP models multivariate time series with latent sub-sequences for diverse behaviors.

Paper proposes LATC for multivariate time series prediction and missing data imputation.

DUET enhances multivariate time series forecasting by clustering time and channels.

A review of contrastive dimension reduction methods for treatment vs control studies.

New algorithms benchmarked for multivariate time series classification.

We exploit an ansatz in order to construct power series expansions for pairs of conjugate functions defined on domains of Euclidean $3$--space. Convergence properties of the resulting series are investigated. Entire solutions which are not harmonic are found as well as a $2$-parameter family of examples which contains …

This paper conditions non-linear infinite-dimensional diffusion processes.

AR model forecasts partially observed dynamical time series by estimating evolution function and imputing missing variables.

Multidimensional time series are sequences of real valued vectors. They occur in different areas, for example handwritten characters, GPS tracking, and gestures of modern virtual reality motion controllers. Within these areas, a common task is to search for similar time series. Dynamic Time Warping (DTW) is a common di…

Generative model combines multi-dimensional annotations for more accurate ground truth estimation.

Study nearest-neighbor radii under dependent sampling, finding they remain informative.

Paper uses autoencoders for time series clustering with energy data.

For geometrically finite hyperbolic manifolds $Γ\backslash H^{n+1}$, we prove the meromorphic extension of the resolvent of Laplacian, Poincaré series, Einsenstein series and scattering operator to the whole complex plane. We also deduce the asymptotics of lattice points of $Γ$ in large balls of $H^{n+1}$ in terms of t…

The paper examines extreme value statistics of high-dimensional sample covariances, with applications in finance and image analysis.

The study classifies Hessian rank 1 hypersurfaces in dimensions 2, 3, and 4.

Given a hyperbolic surface $§$, a classic result of Birman and Series states that for each $K$, all complete geodesics with at most $K$ self-intersections can only pass through a certain nowhere dense, Hausdorff dimension 1 subset of $§$. We define a self-intersection function for each complete geodesic, which bounds t…

Enhances time-series regression trees with latent factors for robust financial analysis.

MPSTime uses matrix-product states for efficient time-series ML.

We give an explicit construction of vertex-transitive tight triangulations of $d$-manifolds for $d\geq 2$. More explicitly, for each $d\geq 2$, we construct two $(d^2+5d+5)$-vertex neighborly triangulated $d$-manifolds whose vertex-links are stacked spheres. The only other non-trivial series of such tight triangulated …

Unified taxonomy categorizes DL-based MTSAD methods.

In this paper we determine all Kobayashi-hyperbolic 2-dimensional complex manifolds for which the group of holomorphic automorphisms has dimension 3. This work concludes a recent series of papers by the author on the classification of hyperbolic $n$-dimensional manifolds, with automorphism group of dimension at least $…

A new framework detects anomalies in multivariate time-series data.

Bayesian QFSTS model tackles feature selection in quantile time series analysis.

New covariance estimator for financial portfolios.

Long Short Term Memory Fully Convolutional Neural Networks (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there has been no study on why L…

The Wythoff construction takes a $d$-dimensional polytope $P$, a subset $S$ of $\{0,..., d\}$ and returns another $d$-dimensional polytope $P(S)$. If $P$ is a regular polytope, then $P(S)$ is vertex-transitive. This construction builds a large part of the Archimedean polytopes and tilings in dimension 3 and 4. We want …

We study sparse principal component analysis for high dimensional vector autoregressive time series under a doubly asymptotic framework, which allows the dimension $d$ to scale with the series length $T$. We treat the transition matrix of time series as a nuisance parameter and directly apply sparse principal component…

In this paper, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series. The architecture is based on the use of a semi-parametric interpolation network followed by the application of a prediction network. The interpolatio…

In this article we present a method by which we can reduce a time series into a single point in $\mathbb{R}^{13}$. We have chosen 13 dimensions so as to prevent too many points from being labeled as "noise." When using a Euclidean (or Mahalanobis) metric, a simple clustering algorithm will with near certainty label the…