Optimized Ridge regression with series-specific preprocessing beats prior linear forecasters and exceeds Transformer, MLP, and CNN baselines on six of eight time-series benchmarks.
Timemixer: Decomposable mul- tiscale mixing for time series forecasting.arXiv preprint arXiv:2405.14616
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
representative citing papers
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
CausalMoE is a multimodal foundation model with pattern-routed heterogeneous experts and LLM/VLM integration that claims new SOTA performance on supervised and few-shot Granger causal discovery benchmarks.
SARAF is a new retrieval-augmented framework for time series forecasting that uses temporal similarity followed by stationarity-modulated diversity selection and aggregation to improve accuracy under non-stationarity.
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
PRISM-CTG is the first large-scale foundation model for cardiotocography that uses multi-view self-supervised learning on unlabeled data to learn transferable representations, outperforming baselines on seven downstream tasks with external validation.
Kairos is a parameter-efficient time series foundation model using dynamic patching tokenizer, mixture-of-size encoding, and spectral-conditioned positional embeddings to improve zero-shot forecasting on heterogeneous data.
UEC-STD is an architecture-agnostic corrector that uses seasonal-trend decomposition to mitigate autoregressive error accumulation in deep forecasters and reports gains across 4 backbones and 10 datasets.
Dynamic Pattern Recalibration (DPR) adds a perceive-route-modulate pipeline that generates time-aware modulation vectors to recalibrate hidden states in forecasting models, improving performance across architectures with low overhead.
CombinationTS decomposes time-series models into modules and finds that good embeddings let simple identity encoders match complex ones, while input structural priors give better performance-stability trade-offs than complex encoders.
CollideNet achieves state-of-the-art time-to-collision forecasting on three public datasets by combining multi-scale spatial aggregation with temporal disentanglement of trend and seasonality in a hierarchical transformer.
CASE-NET combines a causal temporal encoder with adaptive channel recalibration and reports new state-of-the-art accuracy on four of six evaluated multivariate time series tasks.
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.
citing papers explorer
-
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
-
CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts
CausalMoE is a multimodal foundation model with pattern-routed heterogeneous experts and LLM/VLM integration that claims new SOTA performance on supervised and few-shot Granger causal discovery benchmarks.
-
Stationarity-Aware Retrieval-Augmented Time Series Forecasting
SARAF is a new retrieval-augmented framework for time series forecasting that uses temporal similarity followed by stationarity-modulated diversity selection and aggregation to improve accuracy under non-stationarity.
-
What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
-
PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL
PRISM-CTG is the first large-scale foundation model for cardiotocography that uses multi-view self-supervised learning on unlabeled data to learn transferable representations, outperforming baselines on seven downstream tasks with external validation.
-
Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
Kairos is a parameter-efficient time series foundation model using dynamic patching tokenizer, mixture-of-size encoding, and spectral-conditioned positional embeddings to improve zero-shot forecasting on heterogeneous data.
-
Reviving Error Correction in Modern Deep Time-Series Forecasting
UEC-STD is an architecture-agnostic corrector that uses seasonal-trend decomposition to mitigate autoregressive error accumulation in deep forecasters and reports gains across 4 backbones and 10 datasets.
-
Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting
Dynamic Pattern Recalibration (DPR) adds a perceive-route-modulate pipeline that generates time-aware modulation vectors to recalibrate hidden states in forecasting models, improving performance across architectures with low overhead.
-
CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
CombinationTS decomposes time-series models into modules and finds that good embeddings let simple identity encoders match complex ones, while input structural priors give better performance-stability trade-offs than complex encoders.
-
CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting
CollideNet achieves state-of-the-art time-to-collision forecasting on three public datasets by combining multi-scale spatial aggregation with temporal disentanglement of trend and seasonality in a hierarchical transformer.
-
CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification
CASE-NET combines a causal temporal encoder with adaptive channel recalibration and reports new state-of-the-art accuracy on four of six evaluated multivariate time series tasks.
-
Time Series Forecasting Through the Lens of Dynamics
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.