Study reveals benign overfitting in time series models with over-parameterization.
problem Analyzing over-parameterized linear models with dependent time-series data.
method Developed an estimator using interpolation and derived non-asymptotic risk bounds.
result Risk bound is influenced by the coherence of temporal covariance matrices at different time steps.
A parameterization that is a modified version of a previous work is proposed for the returns and correlation matrix of financial time series and its properties are studied. This parameterization allows easy introduction of non-stationarity and it shows several of the characteristics of the true, observed realizations, …
New method reduces DSI complexity using RAE and LSTM for better posterior predictions.
problem Reducing complexity in data-space inversion for subsurface flow simulations.
method Recurrent Autoencoder (RAE) for dimension reduction and LSTM for flow-rate time series representation.
result RAE-based parameterization outperforms existing DSI treatments in statistical agreement with reference results.
Neural networks parameterize time-varying Markov dynamics in financial time series.
problem Estimating Markov transition matrices in high-resolution, high-noise financial data.
method Introduces a neural network framework to generate explicit, time-varying Markov transition matrices, constraining neural outputs to formal stochastic operators.
result Learned operators capture regime shifts, with high-volatility regimes homogenizing transition dynamics.
The paper introduces a method to model error correlations in multivariate time series forecasting.
problem Accurate modeling of error correlations for reliable uncertainty quantification.
method Plug-and-play method that learns error covariance over multiple steps using low-rank-plus-diagonal and independent latent temporal processes.
result Improves predictive accuracy and uncertainty quantification without significantly increasing parameter size.
Sparse Tucker decomposition with graph regularization improves time series forecasting accuracy.
problem High-dimensional time series forecasting with over-parameterization issue.
method Sparse Tucker decomposition and graph regularization for tensor-based model.
result Non-asymptotic error bound and superior performance in numerical experiments.
LLapDiff models irregular multivariate time series without step-by-step integration.
problem Trade-off between discrete and continuous methods for long-horizon forecasting.
method Generative framework that models target as a low-dimensional latent trajectory, guided by modal parameterization and Laplace domain poles.
result Improves long-horizon forecasting over baselines and supports missing-value imputation.
Paper tackles RUL prediction with scarce data using indirect supervision.
problem Predicting RUL with indirect supervision and scarce time series data.
method Unified framework called parameterized static regression, handling data scarcity without interpolation.
result Competitive performance in prediction accuracy with simulated data scarcity.
DMSTF models spatio-temporal data with deep Markov priors.
problem Analyzing nonlinear multimodal spatio-temporal dynamics.
method Deep Markov spatio-temporal factorization with stochastic variational inference.
result DMSTF outperforms other methods in predictive performance and clustering.
TFM trains Neural SDEs without backpropagation, improving clinical time series modeling.
problem Modeling irregularly sampled time series in medicine.
method Trajectory Flow Matching (TFM) using flow matching for generative modeling.
result TFM improves performance on clinical time series datasets.
The study uses Gaussian Processes with Tweedie likelihood for forecasting intermittent time series.
problem Forecasting intermittent time series with high accuracy and flexibility.
method The approach combines Gaussian Processes with two forecast distributions: negative binomial and Tweedie.
result TweedieGP provides better probabilistic forecasts, especially for high quantiles.
New model for time series classification from single example.
problem Classifying time series patterns from limited data.
method Developed a Hidden semi-Markov Model with variable state duration.
result Different representations of state duration have distinct strengths and weaknesses.
Deep state space model forecasts time series with uncertainty.
problem Probabilistic forecasting for risk management.
method Parameterized deep networks for non-linear models, recurrent neural nets for dependency, ARD network for exogenous variables.
result Accurate and sharp probabilistic forecasts with realistic uncertainty growth.
Time series models generalize ARMA and ARFIMA with non-Gaussian dependence.
problem Modeling non-Gaussian serial dependence in time series data.
method Infinite-order partial copula dependence in s-vine processes.
result Rich class of models that generalize linear processes.
NCDSSM models irregularly sampled time series with improved imputation and forecasting.
problem Accurate modeling of irregularly sampled time series with missing observations.
method Neural Continuous-Discrete State Space Model (NCDSSM) with amortized inference for auxiliary variables and flexible dynamic state parameterizations.
result Improved imputation and forecasting performance on multiple benchmark datasets.
This work proposes a method to learn graph structure for multivariate time series forecasting.
problem Improving multivariate time series forecasting by leveraging pairwise information.
method Learning a probabilistic graph model through optimizing mean performance over graph distribution parameterized by a neural network.
result Our method outperforms existing approaches in simplicity, efficiency, and performance.
Proposes a deep generative model for robust forecasting on sparse multivariate time series.
problem Forecasting on sparse multivariate time series with suboptimal results when sparsity is high.
method Dynamic Gaussian Mixture distribution for modeling latent clusters, using neural networks and gating mechanism.
result Demonstrates robust modeling of sparse multivariate time series with improved accuracy.
ACSSM models irregular time series with continuous dynamics.
problem Modeling irregular time series data.
method ACSSM uses a multi-marginal Doob's h-transform and variational inference with stochastic optimal control.
result ACSSM outperforms in tasks like classification, regression, interpolation, and extrapolation.
CRUs model irregular time series with continuous hidden states.
problem Handling irregular time intervals in sequential data.
method Continuous Recurrent Units (CRUs) that integrate hidden states via a linear stochastic differential equation.
result CRUs outperform methods based on neural ordinary differential equations in irregular time series interpolation.
Hybrid models combine domain knowledge and data-driven learning for Earth observation.
problem Challenges in modelling Earth observation data with either purely mechanistic or data-driven methods.
method Gaussian process convolution models, specifically latent force models (LFMs), integrating physical knowledge into multioutput GP models.
result Model automatically estimates soil moisture persistence and discovers latent forces related to precipitation.
NeuTSFlow models continuous functions behind time series forecasting.
problem Forecasting treats time series as discrete sequences, ignoring their continuous nature.
method NeuTSFlow uses Neural Operators to learn the transition between historical and future function families.
result NeuTSFlow outperforms traditional methods in forecasting accuracy and robustness.
Neural Markov models improve time series analysis by balancing deep learning and classical models.
problem Modeling non-stationary time series with high data sparsity.
method Hybrid approach using neural networks to parameterize stochastic matrices, estimating time-inhomogeneous Markov chains.
result Reduction of Chapman-Kolmogorov discrepancy and superior likelihood in financial markets.
This paper corrects climate model biases using a factor model approach.
problem Systematic biases in GCM outputs due to unobserved confounders.
method Factor model approach to learn latent confounders from historical data and apply them to enhance bias correction.
result Significant improvements in the accuracy of precipitation outputs.
This paper proposes a method for modeling event sequences with ambiguous timestamps, a time-discounting convolution. Unlike in ordinary time series, time intervals are not constant, small time-shifts have no significant effect, and inputting timestamps or time durations into a model is not effective. The criteria that …
Noise titration benchmarks time series forecasting models rigorously.
problem Evaluation of time series forecasting models is often flawed due to lack of interventionist methods.
method Interventionist benchmarking using Gaussian noise titration of dynamical systems.
result Fern model outperforms state-of-the-art models in non-stationary conditions.
GRU-D detects age-specific missing patterns in vital signs.
problem Temporal missingness in clinical time series data.
method Gated recurrent unit with decay mechanisms (GRU-D) trained on MIMIC-IV vital signs.
result GRU-D achieves AUROC 0.780 and AUPRC 0.810 on bootstrapped data.
CW-Gen models improve probabilistic time series forecasting by incorporating prior information.
problem Challenges in probabilistic forecasting of multivariate time series due to non-stationarity, inter-variable dependencies, and distribution shifts.
method CW-Gen framework that incorporates prior information through conditional whitening. JMCE learns conditional mean and covariance, improving sample quality.
result CW-Gen consistently enhances predictive performance, capturing non-stationary dynamics and inter-variable correlations more effectively than prior-free approaches.
NANSDE-Net models time series with memory using neural ARMA-type noise.
problem Modeling time series with long- or short-memory characteristics.
method Developed NANSDE-Net, a generative model that incorporates Neural Network-kernel ARMA-type noise.
result NANSDE-Net matches or outperforms existing models in reproducing long- and short-memory features of data.
Detecting the emergence of abrupt property changes in time series is a challenging problem. Kernel two-sample test has been studied for this task which makes fewer assumptions on the distributions than traditional parametric approaches. However, selecting kernels is non-trivial in practice. Although kernel selection fo…
Framework combines random features with CDEs for efficient time-series learning.
problem Efficient training of time-series models with strong inductive bias.
method Random Fourier CDEs and Random Rough DEs using continuous-time reservoirs and log-ODE discretization.
result Unified perspective on random-feature reservoirs and path-signature theory.
We implement gradient-based variational inference routines for Wishart and inverse Wishart processes, which we apply as Bayesian models for the dynamic, heteroskedastic covariance matrix of a multivariate time series. The Wishart and inverse Wishart processes are constructed from i.i.d. Gaussian processes, existing var…
Vanilla convolutional neural networks are known to provide superior performance not only in image recognition tasks but also in natural language processing and time series analysis. One of the strengths of convolutional layers is the ability to learn features about spatial relations in the input domain using various pa…
This paper introduces a new neural ODE model for continuous-time sequence generation.
problem Representing and predicting continuous-time sequences with high accuracy.
method A neural emission model and neural ODE define the latent state evolution, with an Energy-based model for prior distribution.
result The model outperforms existing methods in various tasks, including long-horizon predictions.
We introduce a Bayesian Gaussian process latent variable model that explicitly captures spatial correlations in data using a parameterized spatial kernel and leveraging structure-exploiting algebra on the model covariance matrices for computational tractability. Inference is made tractable through a collapsed variation…
DEPTS learns to forecast periodic time series with improved accuracy.
problem Forecasting periodic time series is challenging due to complex dependencies and diverse periods.
method DEPTS uses a decoupled formulation with an expansion module and a periodicity module to handle these challenges.
result DEPTS significantly improves forecasting accuracy, reducing errors by up to 20%.
We introduce a new category of multivariate conditional generative models and demonstrate its performance and versatility in probabilistic time series forecasting and simulation. Specifically, the output of quantile regression networks is expanded from a set of fixed quantiles to the whole Quantile Function by a univar…
New method for constructing confidence intervals for time series data.
problem Constructing confidence intervals for statistical functionals from time series data.
method Proposes a general purpose confidence interval procedure based on overlapping batches of time series data.
result Large overlapping batches yield confidence intervals of higher quality than generic methods.
Proposes methods to include distributional information in MV-SDEs for better modeling of interacting particle systems.
problem Modeling the behavior of an infinite number of interacting particles with distributional information.
method Semi-parametric methods and estimators for MV-SDEs.
result Explicitly including distributional dependence improves performance in modeling temporal data with interaction.
COT-GAN generates sequential data with a causal optimal transport approach.
problem Generating sequential data with temporal causality constraints.
method Adversarial training with Causal Optimal Transport (COT) and entropic penalization.
result COT-GAN effectively learns time-dependent data distributions and generates stable time series data.
Parameterized state space models in the form of recurrent networks are often used in machine learning to learn from data streams exhibiting temporal dependencies. To break the black box nature of such models it is important to understand the dynamical features of the input driving time series that are formed in the sta…
SALT models combine ARHMM and SLDS for efficient, interpretable time-series analysis.
problem Efficient modeling of systems with time-varying dynamics and long-range dependencies.
method Switching autoregressive low-rank tensor models parameterized with a low-rank factorization.
result SALT models provide a balance of interpretability and efficiency, outperforming ARHMMs and SLDSs.
We consider the problem of learning a Gaussian variational approximation to the posterior distribution for a high-dimensional parameter, where we impose sparsity in the precision matrix to reflect appropriate conditional independence structure in the model. Incorporating sparsity in the precision matrix allows the Gaus…
The paper introduces various canonical parameterizations for 2D-curved shapes.
problem Comparing unparameterized simple curves in the plane.
method Proposes diverse canonical parameterizations, including arc-length and curvature-based.
result Natural parameterizations correspond to physical movements and are geometric invariants.
Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsule…
There are currently two parameterizations used to derive fixed kernels corresponding to infinite width neural networks, the NTK (Neural Tangent Kernel) parameterization and the naive standard parameterization. However, the extrapolation of both of these parameterizations to infinite width is problematic. The standard p…
Proposes a method to train neural networks that solve differential equations faster.
problem Training neural networks that solve differential equations becomes computationally expensive.
method Introduces a differentiable surrogate for numerical solver time cost using higher-order derivatives.
result Trains models that are faster to solve while maintaining nearly the same accuracy.
Paper develops a consistent algorithm for learning graph structure from continuous-time stochastic differential equations.
problem Learning structure from continuous-time stochastic differential equations.
method Score-based structure learning using Neural Ordinary Differential Equations with adaptive regularization.
result The method consistently recovers directed graphs of local independencies in systems of stochastic differential equations.
This paper explores neural models to improve modeling of Hawkes process intensity functions.
problem Traditional Hawkes process intensity function's parametrized kernel function biases future event predictions.
method Uses neural models to model the kernel function of Hawkes process intensity function.
result Neural models can better capture future event characteristics using past events data.