arXiv research

EDAIN layer normalizes time series data for neural networks, improving model performance.

In every point of a Kähler manifold there exist special holomorphic coordinates well adapted to the underlying geometry. Comparing these Kähler normal coordinates with the Riemannian normal coordinates defined via the exponential map we prove that their difference is a universal power series in the curvature tensor and…

GANF uses normalizing flows to detect anomalies in multiple time series.

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when DL is used for financial time series forecasting tasks, where the non-stationary…

For the last few years it has been observed that the Deep Neural Networks (DNNs) has achieved an excellent success in image classification, speech recognition. But DNNs are suffer great deal of challenges for time series forecasting because most of the time series data are nonlinear in nature and highly dynamic in beha…

EvoMSN tackles time series forecasting under distribution shifts by evolving multi-scale normalization.

BiN normalizes financial time-series for better forecasting.

Paper proposes RAN for better anomaly detection in time series data.

We show that the characteristic series for the greedy normal form of a Coxeter group is always a rational series, and prove a reciprocity formula for this series when the group is right-angled and the nerve is Eulerian. As corollaries we obtain many of the known rationality and reciprocity results for the growth series…

A new normalizing flow models continuous stochastic processes efficiently.

Proposes a new normalization method for deep neural networks in financial forecasting.

New method uses G-expectation for financial risk measurement.

FredNormer improves time series forecasting by adapting to frequency domain patterns.

Dimofte, Gaiotto and Gukov introduced a powerful invariant, the 3D-index, associated to a suitable ideal triangulation of a 3-manifold with torus boundary components. The 3D-index is a collection of formal power series in $q^{1/2}$ with integer coefficients. Our goal is to explain how the 3D-index is a generating serie…

We developed a new approach for the analysis of physiological time series. An iterative convolution filter is used to decompose the time series into various components. Statistics of these components are extracted as features to characterize the mechanisms underlying the time series. Motivated by the studies that show …

In this paper we derive a series expansion for the price of a continuously sampled arithmetic Asian option in the Black-Scholes setting. The expansion is based on polynomials that are orthogonal with respect to the log-normal distribution. All terms in the series are fully explicit and no numerical integration nor any …

Improved time series forecasting with multivariate probabilistic models.

Fermat-Torricelli points help assess investment risks by smoothing series data.

Proves convergence of normal forms for infinite-dimensional Lie pseudo-group actions.

A TTA framework improves forecasting accuracy in non-stationary time series.

GAS-Norm improves deep learning time series forecasting in non-stationary settings.

Enhanced time series forecasting with improved trend and seasonal components.

In this paper we present an application of the use of autocopulas for modelling financial time series showing serial dependencies that are not necessarily linear. The approach presented here is semi-parametric in that it is characterized by a non-parametric autocopula and parametric marginals. One advantage of using au…

AIKAE enhances IKAE for long-term time series forecasting.

CN normalizes channels for better time series model performance.

We construct a non-normal affine monoid together with its modules associated with a negative definite plumbed $3$-manifold $M$. In terms of their structure, we describe the $H_1(M,\mathbb{Z})$-equivariant parts of the topological Poincaré series. In particular, we give combinatorial formulas for the Seiberg--Witten inv…

We model non-stationary volume-price distributions with a log-normal distribution and collect the time series of its two parameters. The time series of the two parameters are shown to be stationary and Markov-like and consequently can be modelled with Langevin equations, which are derived directly from their series of …

Bayesian Gaussian Process ODEs enhanced with normalizing flows for improved flexibility and accuracy.

TPA-AD detects axle-box bearing anomalies using pseudo anomalies near normal boundaries.

GANs generate samples from time series data.

This paper reviews self-supervised learning methods for time series anomaly detection.

New framework for tracking varying bounds in time series forecasting.

This is a survey of our research on geometric structures of projective embeddings and includes some topics of our talks in several symposia during 1990-99. We clarify our main problem, which is to construct a kind of geometric composition series of projective embeddings. The concept of "geometric composition series" is…

Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score unseen data samples by computing their exact likelihood under the learned distribution. This makes fl…

ProFITi model forecasts irregular time series with missing values using conditional flows.

Computer vision SSL methods show effectiveness on time series data.

Cash managers make daily decisions based on predicted monetary inflows from debtors and outflows to creditors. Usual assumptions on the statistical properties of daily net cash flow include normality, absence of correlation and stationarity. We provide a comprehensive study based on a real-world cash flow data set from…

Proposes a novel method for generating hard negatives near time series data boundaries.

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…

Variational auto-encoders (VAE) are scalable and powerful generative models. However, the choice of the variational posterior determines tractability and flexibility of the VAE. Commonly, latent variables are modeled using the normal distribution with a diagonal covariance matrix. This results in computational efficien…

This paper tackles time series imputation by identifying and modeling different missing mechanisms.

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

For time series comparisons, it has often been observed that z-score normalized Euclidean distances far outperform the unnormalized variant. In this paper we show that a z-score normalized, squared Euclidean Distance is, in fact, equal to a distance based on Pearson Correlation. This has profound impact on many distanc…

Using classical Taylor series techniques, we develop a unified approach to pricing and implied volatility for European-style options in a general local-stochastic volatility setting. Our price approximations require only a normal CDF and our implied volatility approximations are fully explicit (ie, they require no spec…

Matrix profile has been recently proposed as a promising technique to the problem of all-pairs-similarity search on time series. Efficient algorithms have been proposed for computing it, e.g., STAMP, STOMP and SCRIMP++. All these algorithms use the z-normalized Euclidean distance to measure the distance between subsequ…

DecompKAN improves time series forecasting accuracy and transparency.

Study mapping class groups of cyclic covers, focusing on liftability.

The paper analyzes various normalization methods in deep learning.