השוואת שיטות

	DLinear: מודל לינארי מפורק לחיזוי סדרות עתיות	PatchTST	TSMixer: ארכיטקטורת MLP בלבד לחיזוי סדרות עתיות
תחום	למידה עמוקה	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2023	2023	2023
הוגה השיטה	Ailing Zeng et al.	Nie, Y. et al.	Si-An Chen et al. (Google)
סוג	Decomposition-based linear forecasting model	Transformer for time series forecasting	All-MLP multivariate time-series forecasting model
מקור מכונן	Zeng, A., Chen, M., Zhang, L., & Xu, Q. (2023). Are transformers effective for time series forecasting? AAAI.	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.	Chen, S.-A., Li, C.-L., Yoder, N., Arik, S. O., & Pfister, T. (2023). TSMixer: An all-MLP architecture for time series forecasting. Transactions on Machine Learning Research.
כינויים	Decomposition Linear, DLinear Forecaster, Linear Decomposition Model, Ayrışım Doğrusal Modeli	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer	All-MLP Time Series Mixer, Time Series Mixer, TSMixer Forecasting Model, Zaman Serisi Karıştırıcı
קשורות	3	3	3
תקציר	DLinear is a lightweight time series forecasting model introduced by Zeng et al. at AAAI 2023. It challenges the prevailing assumption that Transformer-based architectures are necessary for accurate long-horizon forecasting. The model decomposes an input sequence into trend and seasonal components using a moving average filter, then applies separate single-layer linear transformations to each component before summing their outputs to produce the final forecast.	PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting.	TSMixer is a multivariate time-series forecasting model introduced by Si-An Chen and colleagues at Google in 2023. It challenges the prevailing dominance of Transformer-based architectures by demonstrating that a simple stack of interleaved MLP layers — alternating between mixing along the time axis and mixing across feature channels — achieves strong forecasting accuracy while remaining computationally efficient and easy to interpret architecturally.