arXiv research

Paper analyzes symbolic-dynamics inspired Markov modeling for time-series data.

A new model for time series using discrete latent states.

Let $G$ be a semisimple Lie group with discrete series. We use maps $K_0(C^*_rG)\to \mathbb{C}$ defined by orbital integrals to recover group theoretic information about $G$, including information contained in $K$-theory classes not associated to the discrete series. An important tool is a fixed point formula for equiv…

In this paper we show that the `quantization commutes with reduction' principle of Guillemin-Sternberg holds for the coadjoint orbits that parametrize the discrete series of a real connected semi-simple Lie group.

Time series data that are not measured at regular intervals are commonly discretized as a preprocessing step. For example, data about customer arrival times might be simplified by summing the number of arrivals within hourly intervals, which produces a discrete-time time series that is easier to model. In this abstract…

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…

Paper develops a gradient-like proposal for discrete distributions without requiring natural differentiability.

NCDSSM models irregularly sampled time series with improved imputation and forecasting.

There is a need for the development of models that are able to account for discreteness in data, along with its time series properties and correlation. Our focus falls on INteger-valued AutoRegressive (INAR) type models. The INAR type models can be used in conjunction with existing model-based clustering techniques to …

In this research the technology of complex Markov chains is applied to predict financial time series. The main distinction of complex or high-order Markov Chains and simple first-order ones is the existing of aftereffect or memory. The technology proposes prediction with the hierarchy of time discretization intervals a…

This work proposes a method to learn graph structure for multivariate time series forecasting.

The discrete-time GARCH methodology which has had such a profound influence on the modelling of heteroscedasticity in time series is intuitively well motivated in capturing many `stylized facts' concerning financial series, and is now almost routinely used in a wide range of situations, often including some where the d…

We provide a simple way to obtain the meromorphic extension of Eisenstein series and Scattering matrices under conditions which generalize the case of discrete groups acting convex cocompactly on hyperbolic spaces.

We detail the theory of Discrete Riemann Surfaces. It takes place on a cellular decomposition of a surface, together with its Poincaré dual, equipped with a discrete conformal structure. A lot of theorems of the continuous theory follow through to the discrete case, we define the discrete analogs of period matrices, Ri…

A new RG approach connects discrete and continuous time descriptions of Gaussian processes.

Study shows Bergman kernels match averages on quotient spaces, proving non-vanishing of Poincaré series.

High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is…

We utilize a recently developed genetic algorithm, in conjunction with discrete wavelets, for carrying out successful forecasts of the trend in financial time series, that includes the NASDAQ composite index. Discrete wavelets isolate the local, small scale variations in these non-stationary time series, after which th…

NeuTSFlow models continuous functions behind time series forecasting.

In this paper we study the analytic realisation of the discrete series representations for the group $G=Sp(1,1)$ as a subspace of the space of square integrable sections in a homogeneous vector bundle over the symmetric space $G/K:=Sp(1,1) /(Sp(1) \times Sp(1))$. We use the Szegö map to give expressions for the restric…

Let $G_0$ be a connected, simply connected real simple Lie group. Suppose that $G_0$ has a compact Cartan subgroup $T_0$, so it has discrete series representations. Relative to $T_0$ there is a distinguished positive root system $Δ^+$ for which there is a unique noncompact simple root $ν$, the "Borel -- de Siebenthal s…

NTW aligns multiple time-series data efficiently using neural networks.

GDM models time series with smoother transitions and interpretable states.

This paper compares two methods for training neural ODEs in time-series regression and CNFs.

A new method scales Gaussian process variational autoencoders to handle high-dimensional time series.

Study new symmetries in non-symmetric spaces and discontinuous groups.

New algorithm uncovers causal relations in non-stationary time series.

Neural CDEs correct errors in learned time-series models for better forecasting.

Let $H<\mathrm{PSL}_2(\mathbb{Z})$ be a finite index normal subgroup which is contained in a principal congruence subgroup, and let $Φ(H)\neq H$ denote a term of the lower central series or the derived series of $H$. In this paper, we prove that the commensurator of $Φ(H)$ in $\mathrm{PSL}_2(\mathbb{R})$ is discrete. W…

Pattern sampling reduces time series classification complexity.

Study on linear independence of Poincaré series for anti-de Sitter 3-manifolds.

simpcomp is an extension to GAP, the well known system for computational discrete algebra. It allows the user to work with simplicial complexes. In the latest version, support for simplicial blowups and discrete normal surfaces was added, both features unique to simpcomp. Furthermore, new functions for constructing cer…

Survey on learning models for irregularly sampled time series data.

Deep learning clusters patient time-series data for better prognosis.

MarketGPT models financial time series with realistic order flow data.

This study examines how discretization improves neural forecasting models.

Novel SVAE learns interpretable discrete data representations from deep learning.

Warped DLMs improve forecasting for count time series.

We study two special cases of the equivariant index defined in part I of this series. We apply this index to deformations of Spin$^c$-Dirac operators, invariant under actions by possibly noncompact groups, with possibly noncompact orbit spaces. One special case is an index defined in terms of multiplicities of discrete…

This paper compares HMM and LSTM for time series forecasting.

This survey is based on a series of lectures that we gave at MSRI in Spring 2015 and on a series of papers, mostly written jointly with Joan Porti. Our goal here is to: 1. Describe a class of discrete subgroups $Γ<G$ of higher rank semisimple Lie groups, which exhibit some "rank 1 behavior". 2. Give different character…

We present an approach to deep estimation of discrete conditional probability distributions. Such models have several applications, including generative modeling of audio, image, and video data. Our approach combines two main techniques: dyadic partitioning and graph-based smoothing of the discrete space. By recursivel…

Improved language models learn complex distributions using Fourier series.

Our purpose is to explore, in the context of loop ensembles on finite graphs, the relations between combinatorial group theory, loops topology, loop measures, and signatures of discrete paths. We determine the distributions of the loop homotopy class, and of the first and second homologies, defined by the lower central…

Estimates impulse response functions using machine learning in time series data.

Sig-Splines model uses signatures and splines for time series data, achieving universality and convexity.

Study on deforming discrete conformal structures on surfaces with boundaries.

The paper maps time-series onto networks to reveal hidden joint information.