Benchmarking time-series foundation models (Chronos-Bolt, zero-shot) vs. supervised (PatchTST) and classical (seasonal-naive, Croston) baselines on the M5 Walmart dataset, scored with MASE and WQL. No single model dominates: foundation/deep models win on dense SKUs, classical methods win on the intermittent tail.
Tokenization Matters: A Fair Ablation of Point-wise, and Variate-wise Transformers for Financial Time Series. (includes PatchTST, iTransformer, Crossformer, Autoformer, Fedformer, Informer, TimeNet, and non-stationarity extensions.
SOTA time-series models for industrial sensor streams · ETT, SWaT · IEEE TII
Comparison of Return Forecasting Methods for Markowitz Portfolio Optimization: Historical Mean, AutoARIMA, PatchTST Transformer
Time-series foundation model fine-tuning toolkit with GPU acceleration
chatbot designed to allow users to interact with transformer models
Heuristics-free self-supervised representation learning for time series with SIGReg (LeJEPA). Disentangles time-axis collapse, positional structure, and representation richness across PatchTST, TCN, and bag-of-patches encoders. Reproducible, seeded, significance-tested.
Disease Forecasting in a Tropical Context: A Comparative Evaluation of Model Performance and Generalizability for Dengue Fever and Influenza in Vietnam
Agentic multi-strategy hedge fund: PatchTST forecasts, 4-agent LangGraph debate, CPCV-OOS + DSR validation, HRP with Ledoit-Wolf shrinkage. 10-year OOS Sharpe=0.766.
PatchTST discharge forecasting with conformal prediction bands — Reno river, station 425 (Progea/TOPKAPI)
Leakage-safe comparison of classical, ML, deep-learning, and zero-shot models for 24-hour Seoul temperature forecasting
Leakage-aware time-series evaluation and online diagnostic replay
Reproducible implementation of adjacent-bin Hermitian projection and controlled VMD reconstruction experiments for one-day-ahead AQI forecasting.
Add a description, image, and links to the patchtst topic page so that developers can more easily learn about it.
To associate your repository with the patchtst topic, visit your repo's landing page and select "manage topics."