Pith. sign in

REVIEW 50 cited by

Long-term Forecasting with TiDE: Time-series Dense Encoder

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.08424 v5 pith:TPFZNZ7U submitted 2023-04-17 stat.ML cs.LG

Abhimanyu Das , Weihao Kong , Andrew Leach , Shaan Mathur , Rajat Sen , Rose Yu This is my paper · ORCID
classification stat.MLcs.LG
keywords time-seriesforecastinglinearlong-termmodelapproachesdenseencoder
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting. Motivated by this, we propose a Multi-layer Perceptron (MLP) based encoder-decoder model, Time-series Dense Encoder (TiDE), for long-term time-series forecasting that enjoys the simplicity and speed of linear models while also being able to handle covariates and non-linear dependencies. Theoretically, we prove that the simplest linear analogue of our model can achieve near optimal error rate for linear dynamical systems (LDS) under some assumptions. Empirically, we show that our method can match or outperform prior approaches on popular long-term time-series forecasting benchmarks while being 5-10x faster than the best Transformer based model.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 50 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 160 citations worldwide. Full citation record

  1. Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond

    cs.LG 2024-12 reject novelty 7.0 of 10

    A theoretical analysis claims attention networks fail to learn residual features when time series steps have opposite signs, giving a possible explanation for the known advantage of linear residual models.

  2. Enhancing Anomaly Resilience in Research Networks: A Large-Scale Forecasting Benchmark for Dynamic Security Baselining

    cs.CR 2026-08 conditional novelty 6.0 of 10

    On a 57-day, ten-router Internet2 traffic corpus, dense MLP forecaster TiDE cuts baseline prediction error by 30 to 42 percent relative to SARIMA and XGBoost, while anomaly masking gives only small robustness gains.

  3. Variable-Horizon Workforce Demand Forecasting with an Aggregate Demand Constraint for Construction Workforce Planning

    cs.CE 2026-08 conditional novelty 6.0 of 10

    A shape-matching method allocates a known remaining workforce budget over a task's remaining duration, preserving the aggregate constraint by construction and beating eight baselines at 5 to 15 day horizons.

  4. A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing

    cs.LG 2026-07 conditional novelty 6.0 of 10

    An adaptive digital twin framework integrating Fisher-score drift detection, LoRA fine-tuning, and Mann-Whitney U validation restores predictive accuracy and uncertainty calibration under concept drift.

  5. Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion

    cs.LG 2026-03 unverdicted novelty 6.0 of 10

    Uncontrolled text–time-series fusion underperforms unimodal baselines; constrained fusion and a low-rank Controlled Fusion Adapter recover gains without changing the TS backbone.

  6. TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

    cs.LG 2025-05 conditional novelty 6.0 of 10

    TimePro forecasts long multivariate series by scanning across variables with a Mamba-like model, then tuning each variable's hidden state at adaptively chosen time points.

  7. Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Forecasting with a non-causal encoder-only model improves fixed-horizon accuracy when the model is asked to output extra future tokens, an effect the authors call delayed chain-of-thought.

  8. Does Scaling Law Apply in Time Series Forecasting?

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A parameter-light adaptive linear model (ALinear) outperforms larger baselines on long-horizon univariate forecasting benchmarks while using under 1% of their parameters, but the efficiency comparison rests on questio...

  9. CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A CNN autoencoder that computes attention scores from variate correlations replaces self-attention, cutting resource use while improving multivariate time-series forecast accuracy.

  10. TimeCapsule: Solving the Jigsaw Puzzle of Long-Term Time Series Forecasting with Compressed Predictive Representations

    cs.LG 2025-04 conditional novelty 6.0 of 10

    TimeCapsule compresses multivariate time series into a small 3D tensor using learned mode products, forecasts inside that compressed space, and reports state-of-the-art results on ten LTSF benchmarks.

  11. Leveraging Hypernetworks and Learnable Kernels for Consumer Energy Forecasting Across Diverse Consumer Types

    cs.LG 2025-02 conditional novelty 6.0 of 10

    HyperEnergy, a hypernetwork that learns LSTM weights with a learnable polynomial/RBF kernel, reports lower 24-hour-ahead energy forecast errors than 10 baselines on most of 10 building datasets.

  12. TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting

    cs.LG 2025-01 conditional novelty 6.0 of 10

    TimeFilter improves multivariate time series forecasting by dynamically filtering a patch-level spatial-temporal graph with a Mixture-of-Experts router, achieving state-of-the-art MSE on 13 benchmarks.

  13. Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation

    cs.LG 2025-01 conditional novelty 6.0 of 10

    TAFAS improves frozen time series forecasters at test time by calibrating inputs and outputs with periodicity-scheduled partial ground truth.

  14. Sensorformer: Cross-patch attention with global-patch compression is effective for high-dimensional multivariate time series forecasting

    cs.LG 2025-01 conditional novelty 6.0 of 10

    Sensorformer uses a two-stage cross-patch attention mechanism with global-patch compression to improve multivariate time series forecasting accuracy while reducing attention complexity.

  15. AI-Enabled Operations at Fermi Complex: Multivariate Time Series Prediction for Outage Prediction and Diagnosis

    cs.LG 2025-01 conditional novelty 6.0 of 10

    On Fermilab Linac data, an LSTM forecast model detects beam outages slightly earlier than Transformer and linear baselines, and a random forest labels their causes with 82% accuracy.

  16. A Comprehensive Forecasting Framework based on Multi-Stage Hierarchical Forecasting Reconciliation and Adjustment

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A hierarchical forecasting system using Bayesian-optimized ensembles plus top-down, MinTrace, harmonic alignment, and stratified scaling produces coherent forecasts, with mixed level-wise accuracy gains across four datasets.

  17. GG-SSMs: Graph-Generating State Space Models

    cs.LG 2024-12 reject novelty 6.0 of 10

    GG-SSMs dynamically build a minimum spanning tree over feature embeddings and propagate SSM state along it, claiming state-of-the-art results on vision and time-series benchmarks.

  18. How Much Can Time-related Features Enhance Time Series Forecasting?

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A lightweight timestamp-encoding module improves long-term forecasting accuracy when blended with existing backbones, especially linear models on electricity and traffic data.

  19. On-Device Adaptive Battery Power Prediction for Electric Vehicles

    cs.LG 2026-07 conditional novelty 5.5 of 10

    On-device online and offline adaptation of pretrained time-series models cuts EV battery power forecast MAE by up to 7.49% and 14.88% under seasonal distribution shift on edge hardware.

  20. Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models

    cs.LG 2026-08 conditional novelty 5.0 of 10

    Reward-based fine-tuning of time series foundation models can collapse predictions away from the true future; steering probability mass into a ground-truth neighborhood reduces that collapse and improves forecasts.

  21. A Predict-then-Correct Loop Based on Few-Shot Continuous Contextual Bandit for Demand Forecasting

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A contextual-bandit correction layer with few-shot masked updates improves ML demand forecasts by 3.7–14.9% and cuts inventory costs in two retail datasets.

  22. Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Exogenous dropout, a model-agnostic whole-channel training mask, restores corruption robustness better than a deliberately bounded gated-FiLM architecture across three forecasting domains.

  23. Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence

    cs.LG 2026-07 conditional novelty 5.0 of 10

    TSFMs need covariates for competitive EPF, do not consistently beat domain-specific methods, and simple TSFM–domain ensembles capture complementary signal under a contamination-aware two-dataset protocol.

  24. FLDmamba: Integrating Fourier and Laplace Transform Decomposition with Mamba for Enhanced Time Series Prediction

    cs.LG 2025-07 conditional novelty 5.0 of 10

    FLDmamba combines a learnable Fourier filter on Mamba's step size with a damped-sinusoid output layer and reports superior long-term forecasting accuracy on standard benchmarks.

  25. Scalable Unsupervised Segmentation via Random Fourier Feature-based Gaussian Process

    cs.LG 2025-07 conditional novelty 5.0 of 10

    RFF-GP-HSMM speeds up unsupervised time-series segmentation by approximating Gaussian processes with random Fourier features, cutting computation time by up to 278 times on motion capture data with similar accuracy.

  26. Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching

    cs.LG 2025-07 conditional novelty 5.0 of 10

    CGFM uses an auxiliary model's predictions as the source for flow matching to learn forecast residuals and improve time series forecasts.

  27. Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives

    cs.LG 2025-06 reject novelty 5.0 of 10

    TimesCLIP aligns image-based and text-based views of the same time series via contrastive learning to improve forecasting accuracy on several benchmarks, but the full multimodal model is not used on two of the six lon...

  28. TFKAN: Time-Frequency KAN for Long-Term Time Series Forecasting

    cs.LG 2025-06 conditional novelty 5.0 of 10

    TFKAN places Kolmogorov-Arnold Networks directly on FFT coefficients alongside a time-domain KAN branch, improving long-term forecast accuracy on seven benchmark datasets.

  29. PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A physics-informed positional encoding that embeds timestamps and latitude/longitude into a vision language model improves typhoon intensity and track forecasting on the Digital Typhoon dataset.

  30. A Multi-scale Representation Learning Framework for Long-Term Time Series Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    MDMixer improves long-term time series forecasting by generating parallel multi-granularity predictions, mixing them from coarse to fine, and adaptively weighting each channel's scales, reaching a 4.64% average MAE re...

  31. OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

    cs.LG 2025-05 conditional novelty 5.0 of 10

    OLinear forecasts time series by decorrelating them with the eigenbasis of their temporal correlation matrix, then applying linear layers; it reports strong accuracy across 24 benchmarks and high efficiency.

  32. Retrieval Augmented Time Series Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    RAFT retrieves the future segments that followed historically similar windows and feeds them to a linear model, cutting forecast error on most of ten benchmarks while losing to the strongest baseline on four.

  33. TSRM: A Lightweight Temporal Feature Encoding Architecture for Time Series Forecasting and Imputation

    cs.LG 2025-04 conditional novelty 5.0 of 10

    A compact CNN-plus-attention architecture, TSRM, is reported to beat or match state-of-the-art models on most forecasting and imputation benchmarks with far fewer parameters.

  34. BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting

    cs.LG 2025-01 reject novelty 5.0 of 10

    BEAT adaptively scales gradients of frequency-specific networks during training to balance learning speeds, with reported gains on some long-term forecasting benchmarks.

  35. Uncertainty-Aware Digital Twins: Robust Model Predictive Control using Time-Series Deep Quantile Learning

    eess.SY 2025-01 conditional novelty 5.0 of 10

    A robust MPC framework that uses one-shot multi-step TiDE predictions and learned quantile bounds as safety tubes, demonstrated on a DED additive-manufacturing simulator.

  36. Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching

    cs.LG 2025-01 conditional novelty 5.0 of 10

    LiPFormer combines a simplified patch-wise Transformer with a CLIP-style contrastive module that exploits future covariates to forecast time series more accurately and efficiently.

  37. Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine

    cs.LG 2024-12 conditional novelty 5.0 of 10

    Judiciously choosing just four datasets can make 46% of forecasting models appear best-in-class and 77% top-three, so dataset selection alone can distort reported performance.

  38. TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion

    cs.LG 2026-07 reject novelty 4.0 of 10

    TFGformer combines STFT-based variable graph learning with covariate fusion and claims small MSE improvements over six baselines on seven time series benchmarks.

  39. N-BEATS-MOE: N-BEATS with a Mixture-of-Experts Layer for Heterogeneous Time Series Forecasting

    cs.LG 2025-08 conditional novelty 4.0 of 10

    Adding a gating network on top of N-BEATS block outputs gives modest SMAPE improvements on some heterogeneous benchmark series, but the gains are small and not statistically validated.

  40. DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting

    cs.AI 2025-07 reject novelty 4.0 of 10

    A dual-channel forecasting architecture combining channel-independent Mamba and channel-mixing linear attention is proposed, but its claimed superiority is contradicted by its own experimental table on several dataset...

  41. Temporal Window Smoothing of Exogenous Variables for Improved Time Series Prediction

    cs.LG 2025-07 conditional novelty 4.0 of 10

    PCA-based reconstruction of exogenous inputs, with a dynamic 90% variance component count, improves transformer forecasting MSE on ETTm1, ETTm2, ETTh1, and Weather, but not on ECL, ETTh2, or Traffic.

  42. Delayformer: spatiotemporal transformation for predicting high-dimensional dynamics

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Delayformer embeds each time series variable into a Hankel matrix, processes the matrices as images with a shared ViT, and predicts all variables in parallel.

  43. CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables

    cs.LG 2025-05 conditional novelty 4.0 of 10

    CrossLinear is a linear time-series forecasting model with a plug-in 1D convolution that mixes exogenous variables into the target, reporting strong but marginally-supported benchmark results.

  44. Data Compression for Time Series Modelling: A Case Study of Smart Grid Demand Forecasting

    cs.CE 2025-05 conditional novelty 4.0 of 10

    Wavelet-based lossy compression can reduce smart-grid sensor data by up to 99% without degrading XGBoost forecasts, but linear models break under the train/test mismatch.

  45. Data-Driven vs Traditional Approaches to Power Transformer's Top-Oil Temperature Estimation

    cs.LG 2025-01 conditional novelty 4.0 of 10

    On a single transformer's data, the ANN, TCN, and TiDE models all forecast top-oil temperature with lower error than the IEC 60076-7 model, while the 98% quantile intervals under-cover substantially.

  46. STTS-EAD: Improving Spatio-Temporal Learning Based Time Series Prediction via

    cs.LG 2025-01 conditional novelty 4.0 of 10

    STTS-EAD embeds anomaly detection into the training loop of a spatio-temporal forecaster and reports 3.8 to 8.1 percent RMSE gains over baselines.

  47. PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN

    cs.LG 2024-12 conditional novelty 4.0 of 10

    PIAD-SRNN outperforms SOTA forecasting models on four indoor CO2 datasets by combining adaptive trend/seasonal decomposition with a physics-inspired state-space RNN.

  48. A Review of the Long Horizon Forecasting Problem in Time Series Analysis

    cs.LG 2025-06 conditional novelty 3.0 of 10

    A survey of long-horizon forecasting with new ETTm2 ablations showing per-timestep error growth that is absent for xLSTM and Triformer.

  49. CATS: Clustering-Aggregated and Time Series for Business Customer Purchase Intention Prediction

    econ.EM 2025-05 reject novelty 3.0 of 10

    A clustering-plus-attention GRU model for next-day customer purchase prediction is tested on four proprietary datasets, claiming consistent gains over baselines.

  50. EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictions

    cs.LG 2024-12 reject novelty 3.0 of 10

    EDformer combines moving-average decomposition with an iTransformer-style variate-token encoder and claims state-of-the-art forecasting, but its reported benchmark results do not consistently support that claim.

Pith tools