方法对比

	Chronos：一种用于时间序列预测的标记化基础模型	长短期记忆网络	TimesFM：面向时间序列预测的仅解码器基础模型
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2024	1997	2024
提出者	Abdul Fatir Ansari et al. (Amazon)	Hochreiter, S. & Schmidhuber, J.	Abhimanyu Das et al. (Google)
类型	Pre-trained language-model-based time-series forecaster	Recurrent neural network (gated memory cell)	Pre-trained decoder-only transformer for zero-shot time-series forecasting
开创性文献	Ansari, A. F., Stella, L., Turkmen, C., Zhang, X., Mercado, P., Shen, H., et al. (2024). Chronos: Learning the language of time series. Transactions on Machine Learning Research.	Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.	Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML.
别名	Chronos Forecasting Model, Amazon Chronos, Tokenized Time-Series LLM, Kronos Zaman Serisi Modeli	LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells	Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli
相关	2	5	3
摘要	Chronos is a family of pre-trained probabilistic forecasting models introduced by Ansari et al. at Amazon in 2024. It adapts the language-model paradigm to time series by quantizing continuous values into discrete tokens, enabling a standard transformer to be trained on a large heterogeneous corpus of time-series data. The result is a zero-shot forecasting model that generalizes across domains without requiring dataset-specific retraining.	LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps.	TimesFM is a pre-trained foundation model for univariate time-series forecasting introduced by Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou from Google in 2024. The model adopts a decoder-only transformer architecture, similar in spirit to large language models, and is trained on a large corpus of real-world and synthetic time-series data. Its central innovation is the ability to perform accurate zero-shot forecasting across diverse domains without task-specific fine-tuning.