Sparse graph learning for dependent time series using ADMM.
problem Inferring conditional independence graph of sparse, high-dimensional stationary multivariate Gaussian time series.
method Sparse-group lasso-based frequency-domain formulation and alternating direction method of multipliers (ADMM) optimization.
result Convergence of inverse PSD estimators to true value under certain conditions.
STanHop predicts multivariate time series with memory-enhanced capabilities.
problem Predicting multivariate time series with memory-enhanced capabilities.
method Sparse Tandem Hopfield Network (STanHop) with two external memory modules.
result STanHop outperforms dense Hopfield models in memory retrieval error.
Motion Code models time series dynamics with sparse approximations.
problem Challenges in time series classification and forecasting on noisy data.
method Motion Code views time series as stochastic processes, assigning unique signatures to distinct dynamics.
result Motion Code outperforms benchmarks in noisy datasets, including real-world Parkinson's disease tracking.
Sparse deep learning improves prediction uncertainty for time series data.
problem Uncertainty quantification for dependent data like time series.
method Sparse recurrent neural networks (RNNs) for time series data.
result Sparse deep learning can consistently estimate and predict time series data with correct uncertainty quantification.
DDD reformulated for sparse matrices, integrating trajectory and snapshot time series data.
problem Efficiently integrate trajectory and snapshot time series data.
method Reformulate DDD to use compact basis functions, reducing parameter scaling.
result Inference of sparse matrices reduces the number of parameters in DDD.
New method for inferring time series graph from sparse-group log-sum penalty.
problem Inferring conditional independence graph from high-dimensional stationary multivariate Gaussian time series.
method Sparse-group log-sum penalty (LSP) and alternating direction method of multipliers (ADMM) for iterative optimization.
result Local convergence of inverse PSD estimators to the true value with rate of convergence.
Paper introduces machine learning for time series data, improving nowcasting accuracy.
problem Improving accuracy in nowcasting US GDP growth using machine learning.
method Sparse-group LASSO estimator for high-dimensional time series data, considering different sampling frequencies and financial/macroeconomic data tail properties.
result Sparse-group LASSO outperforms unstructured LASSO in nowcasting US GDP growth.
Method learns dynamics from sparse, irregular feature data.
problem Learn system dynamics from sparse, irregularly sampled feature time series.
method Formulates as high-dimensional linear regression using signatures.
result Oracle bound on prediction error with explicit sampling dependencies.
We study sparse principal component analysis for high dimensional vector autoregressive time series under a doubly asymptotic framework, which allows the dimension d to scale with the series length T. We treat the transition matrix of time series as a nuisance parameter and directly apply sparse principal component…
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.
We propose a nonparametric method for detecting nonlinear causal relationship within a set of multidimensional discrete time series, by using sparse additive models (SpAMs). We show that, when the input to the SpAM is a β-mixing time series, the model can be fitted by first approximating each unknown function with a …
We tackle anomaly detection in sparse time series data.
problem Sparse time series with low signal-to-noise ratios and non-uniform performance.
method We introduce a novel generative procedure for benchmark datasets and demonstrate how anomaly score smoothing improves performance.
result Anomaly score smoothing consistently improves performance in low-count time series anomaly detection.
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.
The paper introduces a method for interpretable principal component analysis of high-dimensional time series.
problem Inconsistent and difficult-to-interpret principal component estimates in high-dimensional regimes.
method Localized sparse principal component analysis of spectral density matrices in frequency domain.
result Efficient algorithm for sparse-localized estimates of principal subspaces.
Moirai-MoE improves time series forecasting by automatically specializing tokens without human-defined frequency.
problem Unified training on time series data remains challenging due to heterogeneity and non-stationarity.
method Uses sparse mixture of experts (MoE) within Transformers to automatically specialize tokens for diverse time series patterns.
result Moirai-MoE outperforms existing foundation models in both in-distribution and zero-shot scenarios.
The paper develops adaptive deep learning methods for nonlinear time series models.
problem Estimating mean functions of non-stationary and nonlinear time series models.
method Develops non-penalized and sparse-penalized DNN estimators for general non-stationary time series, derives minimax lower bounds, and shows the sparse-penalized DNN estimator is adaptive and optimal.
result Sparse-penalized DNN estimator achieves minimax optimal rates for many nonlinear AR models.
Sparse Markovian Gaussian processes improve probabilistic model inference for large datasets.
problem Efficient inference for large-scale time series data.
method Combining inducing variables with Kalman filter-like recursions for linear scaling.
result General site-based approach for approximating non-Gaussian likelihoods.
Proposes a robust similarity measure for sparse time series data.
problem Sparse time course data in biological settings.
method Gaussian processes (GP) similarity measure based on log-likelihood ratio.
result Enhanced robustness to noise compared to Euclidean distance.
Sparse APCA identifies sparse factors in financial returns over time.
problem Analyzing co-movements of high-dimensional panel data over time.
method Sparse asymptotic PCA with truncated power method for sparse factors and sequential deflation for multi-factor cases.
result Identification of nine risk factors influencing the S&P 500 stock market.
A method for inferring graph from multivariate time series using ADMM.
problem Inferring conditional independence graph from multivariate Gaussian time series.
method Formulated as multi-attribute graph estimation, used ADMM to minimize penalized negative log-likelihood.
result Proposed method outperforms existing frequency-domain approaches in graph edge detection.
DRFormer uses dynamic tokenization and multi-scale transformer to forecast long time series.
problem Forecasting long-term time series data across diverse scales.
method Dynamic tokenizer, multi-scale transformer, dynamic sparse learning, rotary position encoding.
result DRFormer outperforms existing methods in forecasting accuracy.
New method fits sparse Markov models to categorical time series using convex clustering.
problem Exponentially growing parameters in higher-order Markov chains.
method Convex clustering and regularization for parsimonious modeling.
result Theoretical consistency and finite sample performance demonstrated.
In this paper, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series. The architecture is based on the use of a semi-parametric interpolation network followed by the application of a prediction network. The interpolatio…
MAESTRO improves multimodal learning for dynamic time series with adaptive attention and robustness.
problem Challenges in multimodal learning, especially in healthcare and daily living.
method Dynamic intra- and cross-modal interactions, symbolic tokenization, adaptive attention budgeting, sparse cross-modal attention, MoE mechanism.
result Average relative improvements of 4% and 8% over existing multimodal and multivariate approaches, respectively, under complete observations.
Paper uses machine learning for nowcasting corporate earnings from mixed-frequency data.
problem Predicting corporate earnings for a large cross-section of firms with different frequency data.
method Structured machine learning regressions with sparse-group LASSO regularization for panel data.
result Machine learning models outperform traditional methods in nowcasting corporate earnings.
Develops a method to estimate network difference in high-dimensional time series data.
problem Estimating network differences in high-dimensional data can be unreliable.
method Uses an L1 penalty on the difference of inverse spectral densities to estimate network differences.
result Establishes consistency of the method for sparse network differences.
SPADE-S improves time series forecasting accuracy for low-magnitude and sparse data.
problem Challenges in forecasting time series with strong heterogeneity in magnitude and sparsity.
method SPADE-S is a robust forecasting architecture that reduces biases and improves overall prediction accuracy.
result SPADE-S outperforms existing state-of-the-art approaches across diverse use cases, improving forecast accuracy by up to 15%.
Online anomaly detection of time-series data is an important and challenging task in machine learning. Gaussian processes (GPs) are powerful and flexible models for modeling time-series data. However, the high time complexity of GPs limits their applications in online anomaly detection. Attributed to some internal or e…
While most classical approaches to Granger causality detection repose upon linear time series assumptions, many interactions in neuroscience and economics applications are nonlinear. We develop an approach to nonlinear Granger causality detection using multilayer perceptrons where the input to the network is the past t…
Paper develops sparse learning for heavy-tailed time series with locally stationary dynamics.
problem Sparse learning for high-dimensional heavy-tailed locally stationary time series.
method Additive modeling with kernel smoothing, sparsity-inducing penalized estimation.
result Prediction-error bounds and convergence rates for different sparsity structures.
New method forecasts values and timing in irregular time series.
problem Forecasting values and timing in sparse, irregularly sampled multivariate time series.
method Proposes a novel approach for forecasting values and timing in irregular time series.
result Successfully forecasts values and timing in irregular time series.
New model captures insurance risk dependencies efficiently.
problem Dependence modeling in sparse time series of insurance claims.
method Comb-Bernoulli model bridging Lévy copulas and zero-mixed models.
result Model enables tractable simulation, likelihood evaluation, and parameter estimation.
Linear Dynamical System (LDS) is an elegant mathematical framework for modeling and learning multivariate time series. However, in general, it is difficult to set the dimension of its hidden state space. A small number of hidden states may not be able to model the complexities of a time series, while a large number of …
Enhances VAR model estimation using transfer learning.
problem Estimating high-dimensional VAR models with temporal dependencies.
method Transfer learning for VAR models with low-rank and sparse structures.
result Theoretical guarantees for model parameter consistency and informative set selection.
We consider the problem of modeling multivariate time series with parsimonious dynamical models which can be represented as sparse dynamic Bayesian networks with few latent nodes. This structure translates into a sparse plus low rank model. In this paper, we propose a Gaussian regression approach to identify such a mod…
The Vector AutoRegressive (VAR) model is fundamental to the study of multivariate time series. Although VAR models are intensively investigated by many researchers, practitioners often show more interest in analyzing VARX models that incorporate the impact of unmodeled exogenous variables (X) into the VAR. However, sin…
EDICT learns evidential distributions for irregular time series, improving predictions and uncertainty quantification.
problem Challenges in predicting and characterizing uncertainty for irregular time series data.
method EDICT (Evidential Distributions for Irregular Time Series) learns a continuous-time evidential distribution.
result EDICT achieves competitive performance on time series classification tasks and provides better uncertainty quantification.
The paper proposes a new auto-regressive model for multivariate distributional time series.
problem Statistical analysis of multivariate time series of probability measures.
method Wasserstein space, auto-regressive model, iterated random function systems.
result Consistent estimator for auto-regressive coefficients with sparse structure.
Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respe…
Robust PCA detects anomalies and fills gaps in seasonal time series data.
problem Anomaly detection and data imputation in seasonal time series.
method Online robust PCA framework for temporal observations.
result Empirically compared and showed effectiveness in practical situations.
Deep network clusters hospital patients' vital signs.
problem Sparse and irregularly collected vital sign data.
method Deep interpolation network for latent representation extraction.
result Extracted 7 distinct clusters from vital sign data.
New framework IDOL identifies latent causal processes with instantaneous relations from time series data.
problem Identifying latent causal processes with instantaneous relations from time series data.
method Sparse influence constraint and variational inference architecture with sparsity regularization.
result Our method can identify latent causal processes with instantaneous relations.
New sparse GP model learns compositional kernels efficiently.
problem Learning accurate Gaussian Process models with complex kernel structures.
method MultiSVGP model with Horseshoe prior for kernel selection.
result Our model provides better fit and faster computation for large-scale data.
New method infers graph from dependent matrix data.
problem Inferring graph from dependent matrix data.
method Sparse-group lasso-based frequency-domain formulation with ADMM approach.
result Local convergence of inverse PSD estimators to true value.
Proposes a method for forecasting large-scale interval-valued time series.
problem Modeling and forecasting large-scale interval-valued time series.
method Feature extraction procedure involving auto-segmentation, clustering, and precision matrix estimation.
result The method enhances forecasting performance for large-scale interval-valued time series.
Decomposing complex time series into trend, seasonality, and remainder components is an important task to facilitate time series anomaly detection and forecasting. Although numerous methods have been proposed, there are still many time series characteristics exhibiting in real-world data which are not addressed properl…
Paper introduces Native Guide for generating time series counterfactual explanations.
problem Lack of explainability for time series data in AI systems.
method Model-agnostic, instance-based counterfactual generation for time series classification.
result Native Guide produces better counterfactual explanations than benchmarks.
We study Granger causality testing for high-dimensional time series using regularized regressions. To perform proper inference, we rely on heteroskedasticity and autocorrelation consistent (HAC) estimation of the asymptotic variance and develop the inferential theory in the high-dimensional setting. To recognize the ti…