arXiv research

Improved GNN handles long-range dependencies in multi-relational graphs.

Introduces Spectral Attention for better long-range time series forecasting.

Fractal analysis is carried out on the stock market indices of seven European countries and the US. We find evidence of long range dependence in the log return series of the Mibtel (Italy) and the PX Glob (Czech Republic). Long range dependence implies that predictable patterns in the log returns do not dissipate quick…

Novel graph neural network combines random walks with local message passing.

This paper presents empirical evidence using recently developed techniques in econophysics suggesting that the degree of long-range dependence in interest rates depends on the conduct of monetary policy. We study the term structure of interest rates for the US and find evidence that global Hurst exponents change dramat…

This paper studies the dynamics of Brazilian interest rates for short-term maturities. The paper employs developed techniques in the econophysics literature and tests for long-range dependence in the term structure of these interest rates for the last decade. Empirical results suggest that the degree of long-range depe…

IGNN captures long-range graph dependencies using fixed-point equations.

This study uses moving average cluster entropy to analyze financial market dynamics.

New model incorporates long-range dependence in mortality rates for better valuation and risk management.

DRew dynamically rewires message passing to improve long-range tasks.

Representation and learning of long-range dependencies is a central challenge confronted in modern applications of machine learning to sequence data. Yet despite the prominence of this issue, the basic problem of measuring long-range dependence, either in a given data source or as represented in a trained deep model, r…

Improved Mamba model for long-range sequence tasks.

New neural model processes 2D data with long-range dependencies efficiently.

Paper proposes an active learning method for surgical workflow recognition using long-range temporal dependency.

Develops a bi-variate stochastic framework to model mortality and interest rates with long-range dependence.

In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data. Applied on language modelling, our regularizer expresses the inductive bias that sequence variables should have high mutual information even though the model might not see abundant observations for complex lo…

In this paper, we present the results of Monte Carlo simulations for two popular techniques of long-range correlations detection - classical and modified rescaled range analyses. A focus is put on an effect of different distributional properties on an ability of the methods to efficiently distinguish between short and …

Rough Transformers improve efficiency for medical time-series data.

We investigate how simultaneously recorded long-range power-law correlated multi-variate signals cross-correlate. To this end we introduce a two-component ARFIMA stochastic process and a two-component FIARCH process to generate coupled fractal signals with long-range power-law correlations which are at the same time lo…

Study finds long-range dependence in financial markets, but deep generative models struggle to replicate it.

Cointegration helps insurers understand long-range mortality patterns.

We review ideas on temporal dependences and recurrences in discrete time series from several areas of natural and social sciences. We revisit existing studies and redefine the relevant observables in the language of copulas (joint laws of the ranks). We propose that copulas provide an appropriate mathematical framework…

In this paper we present a new framework for time-series modeling that combines the best of traditional statistical models and neural networks. We focus on time-series with long-range dependencies, needed for monitoring fine granularity data (e.g. minutes, seconds, milliseconds), prevalent in operational use-cases. Tra…

Spatial and time-dependent data is of interest in many applications. This task is difficult due to its complex spatial dependency, long-range temporal dependency, data non-stationarity, and data heterogeneity. To address these challenges, we propose Forecaster, a graph Transformer architecture. Specifically, we start b…

Transformer model improves source code summarization.

Investigates RI strategies for life insurers with LRD mortality rates.

Study on SA with heavy-tailed and LRD noise, establishing finite-time bounds.

Combines PCA and message passing for better graph node embeddings.

Self-attention prefers sparse functions of input sequences, reducing sample complexity.

Analysis of long-range dependence in financial time series was one of the initial steps of econophysics into the domain of mainstream finance and financial economics in the 1990s. Since then, many different financial series have been analyzed using the methods standardly used outside of finance to deliver some importan…

In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics. Because of their sequential nature, RNNs are good at capturing the local structure of a word sequence - both semantic and syn…

A new algorithm for restless bandits handles long-range dependencies.

We consider the estimation of large covariance and precision matrices from high-dimensional sub-Gaussian or heavier-tailed observations with slowly decaying temporal dependence. The temporal dependence is allowed to be long-range so with longer memory than those considered in the current literature. We show that severa…

We propose a multiresolution Gaussian process to capture long-range, non-Markovian dependencies while allowing for abrupt changes. The multiresolution GP hierarchically couples a collection of smooth GPs, each defined over an element of a random nested partition. Long-range dependencies are captured by the top-level GP…

Approximates derivative pricing under fractional stochastic volatility.

A main theoretical interest in biology and physics is to identify the nonlinear dynamical system (DS) that generated observed time series. Recurrent Neural Networks (RNNs) are, in principle, powerful enough to approximate any underlying DS, but in their vanilla form suffer from the exploding vs. vanishing gradients pro…

Characterizing temporal dependence patterns is a critical step in understanding the statistical properties of sequential data. Long Range Dependence (LRD) --- referring to long-range correlations decaying as a power law rather than exponentially w.r.t. distance --- demands a different set of tools for modeling the unde…

This paper examines multifractal dynamics in cryptocurrencies using two methodologies.

In this paper we extend the theory of option pricing to take into account and explain the empirical evidence for asset prices such as non-Gaussian returns, long-range dependence, volatility clustering, non-Gaussian copula dependence, as well as theoretical issues such as asymmetric information and the presence of limit…

Analyzed a generalized voter model with power-law herding intensity, revealing anomalous diffusion and long-range memory.

Graph neural networks struggle to propagate long-range information, causing over-squashing.

We present the mixture-of-parents maximum entropy Markov model (MoP-MEMM), a class of directed graphical models extending MEMMs. The MoP-MEMM allows tractable incorporation of long-range dependencies between nodes by restricting the conditional distribution of each node to be a mixture of distributions given the parent…

Transformers improve time series modeling by capturing long-range dependencies.

A method for estimating the cross-correlation $C_{xy}(τ)$ of long-range correlated series $x(t)$ and $y(t)$, at varying lags $τ$ and scales $n$, is proposed. For fractional Brownian motions with Hurst exponents $H_1$ and $H_2$, the asymptotic expression of $C_{xy}(τ)$ depends only on the lag $τ$ (wide-sense stationarit…

Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature interactions within finite receptive fields while recurrent architectures can be slow and …

Several machine learning problems arising in natural language processing can be modeled as a sequence labeling problem. We provide Gaussian process models based on pseudo-likelihood approximation to perform sequence labeling. Gaussian processes (GPs) provide a Bayesian approach to learning in a kernel based framework. …

The paper considers the block sampling method for long-range dependent processes. Our theory generalizes earlier ones by Hall, Jing and Lahiri (1998) on functionals of Gaussian processes and Nordman and Lahiri (2005) on linear processes. In particular, we allow nonlinear transforms of linear processes. Under suitable c…

Improved flow-based models capture dependencies better with multi-scale autoregressive priors.