arXiv research

CRCCA framework improves non-linear CCA with compressed representations.

Methodology to measure non-linear correlations using copulas and clustering.

Proposes $\ell_0$-CCA for sparse CCA with improved representation learning.

We introduce the Randomized Dependence Coefficient (RDC), a measure of non-linear dependence between random variables of arbitrary dimension based on the Hirschfeld-Gebelein-Rényi Maximum Correlation Coefficient. RDC is defined in terms of correlation of random non-linear copula projections; it is invariant with respec…

New algorithm for faster support recovery in quadratic logistic regression.

In the last years efforts in econophysics have been shifted to study how network theory can facilitate understanding of complex financial markets. Main part of these efforts is the study of correlation-based hierarchical networks. This is somewhat surprising as the underlying assumptions of research looking at financia…

Study reveals cash flow data is non-linear, impacting forecasting methods.

The study uses DCC for financial market analysis, revealing hidden correlations.

New Shapley values reveal non-linear feature dependencies.

CVAE improves stock volume forecasting with advanced input variables.

The article generalizes Pearson correlation to Riemannian manifolds.

In this paper we briefly review the recently inrtroduced Multifractal Random Walk (MRW) that is able to reproduce most of recent empirical findings concerning financial time-series : no correlation between price variations, long-range volatility correlations and multifractal statistics. We then focus on its extension t…

End-to-end CCA optimizes both discriminative and latent space projections for multi-view learning.

Financial markets are complex adaptive systems, and are commonly studied as complex networks. Most of such studies fall short in two respects: they do not account for non-linearity of the studied relationships, and they create one network for the whole studied time series, providing an average picture of a very long, e…

DART optimizes subset selection in non-linear bandit problems.

Machine learning improves joint default assessment by capturing non-linear dependencies.

Combining neural networks and multiscale decomposition for financial market analysis.

We develop algorithms to learn non-linear dynamical systems without mixing assumptions.

Financial time series exhibit two different type of non linear correlations: (i) volatility autocorrelations that have a very long range memory, on the order of years, and (ii) asymmetric return-volatility (or `leverage') correlations that are much shorter ranged. Different stochastic volatility models have been propos…

Investigates financial and economic systems using statistical mechanics and information theory.

ChatGPT predicts stock market movements based on Bloomberg headlines, showing a positive correlation over short to medium terms.

Entropy-Isomap improves low-dimensional visualization of dynamic processes.

Tutorial explains various canonical correlation methods.

Study on dynamics of non-linear autoencoders learning principal components.

Improved control approach for correlated bandits with better performance.

Proposes MFI for non-linear learning to explain complex feature interactions.

Study neural networks by mapping correlations, revealing essential statistics.

The study identifies factors predicting stock returns and maximum drawdown using various models.

In this article we analyse linear correlation and non-linear dependence of traded volume, $v$, of the 30 constituents of Dow Jones Industrial Average at different value scales. Specifically, we have raised $v$ to some real value $α$ or $β$, which introduces a bias for small ($α, β<0$) or large ($α, β>1$) values. Our r…

The study uncovers stock synergy networks using mutual information in Indian stock market data.

Non-linear image reconstruction and signal analysis deal with complex inverse problems. To tackle such problems in a systematic way, I present information field theory (IFT) as a means of Bayesian, data based inference on spatially distributed signal fields. IFT is a statistical field theory, which permits the construc…

Most data is multi-dimensional. Discovering whether any subset of dimensions, or subspaces, of such data is significantly correlated is a core task in data mining. To do so, we require a measure that quantifies how correlated a subspace is. For practical use, such a measure should be universal in the sense that it capt…

Gaussian processes emulate complex non-linear models efficiently.

The paper proposes new cross-correlators using Price's Theorem and piecewise-linear decomposition.

Develops a new model for deep structured prediction with non-linear output transformations.

We study the dynamics of the linear and non-linear serial dependencies in financial time series in a rolling window framework. In particular, we focus on the detection of episodes of statistically significant two- and three-point correlations in the returns of several leading currency exchange rates that could offer so…

Bayesian model merges multi-view latent models and kernel methods.

We investigate the behavior of stocks in daily price-limited stock markets by purposing a quantum spatial-periodic harmonic model. The stock price is presumed to oscillate and damp in a quantum spatial-periodic harmonic oscillator potential well. Complicated non-linear relations including inter-band positive correlatio…

We introduce two types of ordinal pattern dependence between time series. Positive (resp. negative) ordinal pattern dependence can be seen as a non-paramatric and in particular non-linear counterpart to positive (resp. negative) correlation. We show in an explorative study that both types of this dependence show up in …

Method estimates mixture components without discretizing parameters.

Wiener-Granger causality is a widely used framework of causal analysis for temporally resolved events. We introduce a new measure of Wiener-Granger causality based on kernelization of partial canonical correlation analysis with specific advantages in the context of large high-dimensional data. The introduced measure is…

A new method bypasses regularization for disentangled latent variables without tuning.

Deep networks prioritize easier examples over harder ones, leading to faster training.

The distribution of the return intervals $τ$ between volatilities above a threshold $q$ for financial records has been approximated by a scaling behavior. To explore how accurate is the scaling and therefore understand the underlined non-linear mechanism, we investigate intraday datasets of 500 stocks which consist of …

Regularizes GAMs to improve interpretability by reducing concurvity.

Two new algorithms reduce feature space while preserving non-linear relationships.

Modeling correlated mutations in cancer for personalized treatment.

In this paper we consider sparse and identifiable linear latent variable (factor) and linear Bayesian network models for parsimonious analysis of multivariate data. We propose a computationally efficient method for joint parameter and model inference, and model comparison. It consists of a fully Bayesian hierarchy for …