Papers

Field

Top tools here

Open problems in Forecasting time

Event-driven time series forecasting1 paper raises it · 2 address it
Real-world time series are often influenced by exogenous events, which conventional models ignore.
- SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecastingraises · addresses
- TimeBraid: Unifying Time Series and Language for Understanding and Forecastingaddresses
Trade-off between accuracy and distributional realism in forecasting1 paper raises it · 2 address it
Models often excel at either prediction accuracy or distributional realism, but not both.
- Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspectiveraises · addresses
- PathFM: Fast Generative Forecasting of Multivariate Trajectoriesaddresses
Dependence structure modeling in multivariate forecasting1 paper raises it · 1 addresses it
Most models predict marginal quantiles, ignoring the dependence structure of future trajectories.
- PathFM: Fast Generative Forecasting of Multivariate Trajectoriesraises · addresses
Interpretability in sequential event prediction1 paper raises it · 1 addresses it
Existing methods prioritize accuracy over explainability, which is critical in many applications.
- What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rulesraises · addresses
Zero-shot forecasting for domain-specific data1 paper raises it · 1 addresses it
Foundation models struggle with zero-shot performance in specialized domains like soil moisture forecasting.
- Zero-Shot Forecasting of In-Situ Soil Moisture and Temperature with a Time-Series Foundation Modelraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

forecasting time · forecasters · forecasting203 papers26 this week
weather forecasting · weather prediction · forecasts166 papers20 this week
financial forecasting · based trading · price forecasting79 papers14 this week
data assimilation · forecast · probabilistic forecasting66 papers6 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGSep 26
Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning
Junyi Wang, Yilin Wang, Wen Wu, Chao Zhang
LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and guide the sequence of actions required to complete forecasting tasks. Most existing agents focus only on the current forecasting instance. However, in real-world deployments, forecasting commonly operates online, with new forecasts issued from the currently available history as the forecast origin advances and the ground-truth targets of earlier instances progressively become available. These targets provide feedback on the actions taken in earlier instances, yet existing agents generally do not preserve or utilise this information to adapt their subsequent actions. To address this limitation, we introduce FASE, a Feedback-Aware Self-Evolving forecasting agent that converts such feedback into task-specific experience for subsequent forecasting instances. FASE combines episodic memory, which retrieves relevant completed instances, with online policy learning, which summarises the feedback accumulated across instances into ranking guidance. The proposed framework is evaluated on 29 dataset configurations selected from the GIFT-Eval…
PDF arXiv
arXiv cs.AISep 26
MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off
Ibram Abdelmalak, Mischa Putzke, Jungmin Choi, Tom Hanika, Vijaya Krishna Yalavarthi +1
Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about the future of another. Yet they are evaluated on a small fixed set of standard datasets whose cross-channel structure is rarely examined. We ask two questions: "How can we reliably measure lagged, non-linear, and joint coupling in MTSF datasets?" and "Do the standard datasets actually have such coupling?" To answer the first, we test four candidate measures on synthetic datasets with planted ground-truth coupling: Granger Causality (GC), Transfer Entropy (TE), lagged Mutual Information (MI), and the CD gain, a model-based measure we introduce that compares a channel-dependent (CD) model to its channel-independent (CI) variant. Only lagged MI and the CD gain recover every planted coupling. For the second question, the answer is a definite no, as the standard datasets have a median of only 23% lagged-coupled channel pairs and a median CD gain of -4.9%, compared to 78% and +4.6% on chaotic ODE systems. We therefore propose MixBench-TS, a benchmark of 10 real-world datasets with a median of 55.5% lagged-coupled pairs and a median CD…
PDF arXiv
arXiv eess.SYSep 26
Schur-Neural KF: Learned Schur-Consistent Corrections to the Extended Kalman Filter
Min Kim, Lianghao Cao, Soon-Jo Chung, Andrew M. Stuart
We present Schur-Neural KF (SN-KF), a learning-based correction to the extended Kalman filter (EKF) that preserves the probabilistic conditioning interpretation of the EKF. The method perturbs the predictive state-measurement cross-covariance and the Cholesky factor of the measurement noise covariance so that the resulting joint predictive covariance is always positive semidefinite. The positive semidefiniteness is ensured by a Schur complement-based parametrization. We instantiate the parametrization with a recurrent neural architecture whose matrix outputs are modulated by amplitude gates. We prove that incorporating a measurement does not increase the filter's state uncertainty, and show that no measurement can induce an arbitrarily large state correction relative to its statistical surprise. We also present a perturbative analysis suggesting SN-KF's structural strength in the data-scarce regime. We provide two numerical experiments to illustrate the practical benefits of SN-KF. In a two-radar experiment, enforcing Schur-consistency provides a much broader failure-free hyperparameter region and reduces RMSE for small training subsets, consistent with our theoretical analysis…
PDF arXiv
arXiv cs.LGSep 26
Rondo: Unsupervised Discovery of Recurring Temporal Structure
Yingtian Shi, Ankith Chandra, Thomas Plötz
Many real-world time series data exhibit structural properties at multiple scales, from short, recurring units to complex sequences composed of these units. Unsupervised discovery of both these components and structure enables the design of intelligent systems that help interpret temporal data, thereby limiting the amount of costly human annotations required. Existing modeling approaches typically overlook the hierarchical structure inherent to many time series, treating recurring patterns at different temporal scales as independent structures. Moreover, most assume access to the complete data sequence and treat discovery as a static process, limiting their ability to evolve as new observations arrive. We introduce Rondo, an unsupervised approach for modeling recurring hierarchical structure in continuous temporal streams. By explicitly constructing vocabularies of reusable units and their recurring compositions, Rondo captures structure shared across complex temporal patterns while refining and expanding its discoveries as the stream evolves. Evaluations on temporal sequences spanning diverse domains and data modalities show that Rondo outperforms existing unsupervised…
PDF arXiv
arXiv stat.MLSep 26
AECSF: Adaptive Ensemble Conditional Score Filtering for High-Dimensional Nonlinear Data Assimilation
Yangwen Zhang, Shiwei Ni, Xiaoping Zhang, Xiaofei Guan, Lili Ju
Bayesian state estimation for high-dimensional nonlinear dynamical systems entails a fundamental tension between statistical fidelity and computational tractability, as particle weights can collapse, while Gaussian ensemble updates can miss non-Gaussian posterior structure. Score-based diffusion filters offer a sampling-based alternative, but existing training-free score filters often rely on heuristic likelihood corrections, which can compromise posterior accuracy by neglecting uncertainty about the system state associated with each noisy reverse particle. To address these issues, we propose AECSF, a training-free adaptive ensemble conditional score filter. AECSF constructs an analytically tractable score estimator from the conditional Tweedie identity, which recasts noisy posterior score estimation as estimating the conditional mean of the system state given a noisy reverse particle and the observation. To estimate these conditional means efficiently, AECSF employs a shared adaptive weighted proposal ensemble, while particle-specific conditional weights yield an estimate for each noisy reverse particle without separate proposal sampling. The proposal ensemble is updated using…
PDF arXiv
arXiv cs.LGSep 26
TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
Weiwei Ye, Renhe Jiang, Hangchen Liu, Dongyuan Li, Yoshihide Sekimoto
Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offers a natural lens to model time series, current deep learning approaches do not explicitly model evolution and randomness in the Fourier spectra, which limits their ability to accurately predict both the expected trajectory and its uncertainty in non-stationary time series. Motivated by Evolutionary Spectra (ES) theory, we propose TimeES, a general framework that enables probabilistic and deterministic forecasting via the evolutionary spectra theory. Specifically, we derive a parameterizable evolutionary spectra formulation, recasting non-stationary random process modeling as learning an evolving representation modulated by random variables. Furthermore, we reduce the complexity of the estimated spectra from O(NM) to O(NK), where K << M/2, by exploiting Hermitian symmetry and spectral energy sparsity for frequency selection. Based on a simple linear backbone, our proposed TimeES achieves consistent state-of-the-art performance across both deterministic and probabilistic forecasting tasks, with high efficiency and interpretability.…
PDF arXiv

Papers

Topics in this field

forecasting time · forecasters · forecasting203 papers26 this week
weather forecasting · weather prediction · forecasts166 papers20 this week
financial forecasting · based trading · price forecasting79 papers14 this week
data assimilation · forecast · probabilistic forecasting66 papers6 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.LGSep 26
Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning
Junyi Wang, Yilin Wang, Wen Wu, Chao Zhang
LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and guide the sequence of actions required to complete forecasting tasks. Most existing agents focus only on the current forecasting instance. However, in real-world deployments, forecasting commonly operates online, with new forecasts issued from the currently available history as the forecast origin advances and the ground-truth targets of earlier instances progressively become available. These targets provide feedback on the actions taken in earlier instances, yet existing agents generally do not preserve or utilise this information to adapt their subsequent actions. To address this limitation, we introduce FASE, a Feedback-Aware Self-Evolving forecasting agent that converts such feedback into task-specific experience for subsequent forecasting instances. FASE combines episodic memory, which retrieves relevant completed instances, with online policy learning, which summarises the feedback accumulated across instances into ranking guidance. The proposed framework is evaluated on 29 dataset configurations selected from the GIFT-Eval…
PDF arXiv
arXiv cs.AISep 26
MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off
Ibram Abdelmalak, Mischa Putzke, Jungmin Choi, Tom Hanika, Vijaya Krishna Yalavarthi +1
Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about the future of another. Yet they are evaluated on a small fixed set of standard datasets whose cross-channel structure is rarely examined. We ask two questions: "How can we reliably measure lagged, non-linear, and joint coupling in MTSF datasets?" and "Do the standard datasets actually have such coupling?" To answer the first, we test four candidate measures on synthetic datasets with planted ground-truth coupling: Granger Causality (GC), Transfer Entropy (TE), lagged Mutual Information (MI), and the CD gain, a model-based measure we introduce that compares a channel-dependent (CD) model to its channel-independent (CI) variant. Only lagged MI and the CD gain recover every planted coupling. For the second question, the answer is a definite no, as the standard datasets have a median of only 23% lagged-coupled channel pairs and a median CD gain of -4.9%, compared to 78% and +4.6% on chaotic ODE systems. We therefore propose MixBench-TS, a benchmark of 10 real-world datasets with a median of 55.5% lagged-coupled pairs and a median CD…
PDF arXiv
arXiv eess.SYSep 26
Schur-Neural KF: Learned Schur-Consistent Corrections to the Extended Kalman Filter
Min Kim, Lianghao Cao, Soon-Jo Chung, Andrew M. Stuart
We present Schur-Neural KF (SN-KF), a learning-based correction to the extended Kalman filter (EKF) that preserves the probabilistic conditioning interpretation of the EKF. The method perturbs the predictive state-measurement cross-covariance and the Cholesky factor of the measurement noise covariance so that the resulting joint predictive covariance is always positive semidefinite. The positive semidefiniteness is ensured by a Schur complement-based parametrization. We instantiate the parametrization with a recurrent neural architecture whose matrix outputs are modulated by amplitude gates. We prove that incorporating a measurement does not increase the filter's state uncertainty, and show that no measurement can induce an arbitrarily large state correction relative to its statistical surprise. We also present a perturbative analysis suggesting SN-KF's structural strength in the data-scarce regime. We provide two numerical experiments to illustrate the practical benefits of SN-KF. In a two-radar experiment, enforcing Schur-consistency provides a much broader failure-free hyperparameter region and reduces RMSE for small training subsets, consistent with our theoretical analysis…
PDF arXiv
arXiv cs.LGSep 26
Rondo: Unsupervised Discovery of Recurring Temporal Structure
Yingtian Shi, Ankith Chandra, Thomas Plötz
Many real-world time series data exhibit structural properties at multiple scales, from short, recurring units to complex sequences composed of these units. Unsupervised discovery of both these components and structure enables the design of intelligent systems that help interpret temporal data, thereby limiting the amount of costly human annotations required. Existing modeling approaches typically overlook the hierarchical structure inherent to many time series, treating recurring patterns at different temporal scales as independent structures. Moreover, most assume access to the complete data sequence and treat discovery as a static process, limiting their ability to evolve as new observations arrive. We introduce Rondo, an unsupervised approach for modeling recurring hierarchical structure in continuous temporal streams. By explicitly constructing vocabularies of reusable units and their recurring compositions, Rondo captures structure shared across complex temporal patterns while refining and expanding its discoveries as the stream evolves. Evaluations on temporal sequences spanning diverse domains and data modalities show that Rondo outperforms existing unsupervised…
PDF arXiv
arXiv stat.MLSep 26
AECSF: Adaptive Ensemble Conditional Score Filtering for High-Dimensional Nonlinear Data Assimilation
Yangwen Zhang, Shiwei Ni, Xiaoping Zhang, Xiaofei Guan, Lili Ju
Bayesian state estimation for high-dimensional nonlinear dynamical systems entails a fundamental tension between statistical fidelity and computational tractability, as particle weights can collapse, while Gaussian ensemble updates can miss non-Gaussian posterior structure. Score-based diffusion filters offer a sampling-based alternative, but existing training-free score filters often rely on heuristic likelihood corrections, which can compromise posterior accuracy by neglecting uncertainty about the system state associated with each noisy reverse particle. To address these issues, we propose AECSF, a training-free adaptive ensemble conditional score filter. AECSF constructs an analytically tractable score estimator from the conditional Tweedie identity, which recasts noisy posterior score estimation as estimating the conditional mean of the system state given a noisy reverse particle and the observation. To estimate these conditional means efficiently, AECSF employs a shared adaptive weighted proposal ensemble, while particle-specific conditional weights yield an estimate for each noisy reverse particle without separate proposal sampling. The proposal ensemble is updated using…
PDF arXiv
arXiv cs.LGSep 26
TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
Weiwei Ye, Renhe Jiang, Hangchen Liu, Dongyuan Li, Yoshihide Sekimoto
Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offers a natural lens to model time series, current deep learning approaches do not explicitly model evolution and randomness in the Fourier spectra, which limits their ability to accurately predict both the expected trajectory and its uncertainty in non-stationary time series. Motivated by Evolutionary Spectra (ES) theory, we propose TimeES, a general framework that enables probabilistic and deterministic forecasting via the evolutionary spectra theory. Specifically, we derive a parameterizable evolutionary spectra formulation, recasting non-stationary random process modeling as learning an evolving representation modulated by random variables. Furthermore, we reduce the complexity of the estimated spectra from O(NM) to O(NK), where K << M/2, by exploiting Hermitian symmetry and spectral energy sparsity for frequency selection. Based on a simple linear backbone, our proposed TimeES achieves consistent state-of-the-art performance across both deterministic and probabilistic forecasting tasks, with high efficiency and interpretability.…
PDF arXiv

Activity · 12 weeks

Open problems in Forecasting time

Event-driven time series forecasting1 paper raises it · 2 address it
Real-world time series are often influenced by exogenous events, which conventional models ignore.
- SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecastingraises · addresses
- TimeBraid: Unifying Time Series and Language for Understanding and Forecastingaddresses
Trade-off between accuracy and distributional realism in forecasting1 paper raises it · 2 address it
Models often excel at either prediction accuracy or distributional realism, but not both.
- Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspectiveraises · addresses
- PathFM: Fast Generative Forecasting of Multivariate Trajectoriesaddresses
Dependence structure modeling in multivariate forecasting1 paper raises it · 1 addresses it
Most models predict marginal quantiles, ignoring the dependence structure of future trajectories.
- PathFM: Fast Generative Forecasting of Multivariate Trajectoriesraises · addresses
Interpretability in sequential event prediction1 paper raises it · 1 addresses it
Existing methods prioritize accuracy over explainability, which is critical in many applications.
- What Comes Next and Why: Interpretable Next-Event Prediction with Neuro-Symbolic Rulesraises · addresses
Zero-shot forecasting for domain-specific data1 paper raises it · 1 addresses it
Foundation models struggle with zero-shot performance in specialized domains like soil moisture forecasting.
- Zero-Shot Forecasting of In-Situ Soil Moisture and Temperature with a Time-Series Foundation Modelraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 54m ago

Forecasting time

Found by the topic model: forecasting time, weather forecasting, financial forecasting.

66papers this week−15.4% vs last week

All papers · 514 With code · 4

Newest Most relevant

427 papers this month