পদ্ধতির তুলনা করুন

	Autoformer: দীর্ঘমেয়াদী সময়-সিরিজ পূর্বাভাসের জন্য ডিকম্পোজিশন ট্রান্সফরমার	FEDformer: ফ্রিকোয়েন্সি এনহ্যান্সড ডিকম্পোজড ট্রান্সফরমার	স্টেট স্পেস মডেল (কালম্যান ফিল্টার)
ক্ষেত্র	গভীর শিখন	গভীর শিখন	অর্থমিতি
পরিবার	Machine learning	Machine learning	Regression model
উদ্ভবের বছর	2021	2022	1990
প্রবর্তক	Haixu Wu et al. (Tsinghua)	Tian Zhou et al.	Harvey; Durbin & Koopman (state space treatment); Kalman filter
ধরন	Decomposition-based deep forecasting model	Frequency-domain decomposed Transformer for time-series forecasting	State space time series model
মৌলিক উৎস	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. ICML.	Harvey, A. C. (1990). Forecasting, Structural Time Series Models and the Kalman Filter. Cambridge University Press.
অপর নাম	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Frequency Enhanced Decomposed Transformer, FED-Transformer, Frequency Domain Transformer, Frekans Tabanlı Ayrıştırılmış Dönüştürücü	state space, Kalman filter, unobserved components model, Durum Uzayı Modeli (State Space / Kalman Filter)
সম্পর্কিত	4	3	4
সারসংক্ষেপ	Autoformer is a deep learning architecture for long-term time-series forecasting, introduced by Wu et al. from Tsinghua University at NeurIPS 2021. It replaces the standard self-attention mechanism with an Auto-Correlation mechanism that exploits periodic dependencies in the frequency domain, and embeds a progressive series decomposition block throughout the encoder and decoder to separately model trend and seasonal components.	FEDformer is a Transformer-based architecture for long-term multivariate time-series forecasting, introduced by Zhou et al. at ICML 2022. Its core innovation is the combination of seasonal-trend decomposition with frequency-domain attention: instead of computing full token-to-token attention in the time domain, FEDformer projects queries, keys, and values into the frequency domain via Fourier or wavelet transforms and operates on a randomly selected subset of frequency components, achieving linear complexity while preserving global temporal structure.	A state space model is a general time series framework that describes a series through unobserved (latent) state variables linked by a measurement equation and a transition equation, with the states estimated in real time by the Kalman filter. Developed in the state space tradition of Harvey (1990) and Durbin & Koopman (2012), it nests ARIMA and exponential smoothing as special cases.