paper-with-me

Papers

Long-term Forecasting using Tensor-Train RNNs

2018-01-01 · ICLR 2018 1 · Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue

We present Tensor-Train RNN (TT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics. Long-term forecasting in such systems is highly challenging, since there exist long-term temporal dependencies, higher-order correlations and sensitivity to error propagation. Our proposed tensor recurrent architecture addresses these issues by learning the nonlinear dynamics directly using higher order moments and high-order state transition functions. Furthermore, we decompose the higher-order structure using the tensor-train (TT) decomposition to reduce the number of parameters while preserving the model performance. We theoretically establish the approximation properties of Tensor-Train RNNs for general sequence inputs, and such guarantees are not available for usual RNNs. We also demonstrate significant long-term prediction improvements over general RNN and LSTM architectures on a range of simulated environments with nonlinear dynamics, as well on real-world climate and traffic data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Long-term Forecasting using Higher Order Tensor RNNs

2017-10-31 · ICLR 2018 1 · Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue

We present Higher-Order Tensor RNN (HOT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics. Long-term forecasting in such systems is highly challeng…

Time SeriesTime Series Analysis

DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series

2023-08-26 · Chaoqun Wang, Yijun Li, Xiangqian Sun, Qi Wu 외

Time series forecasting is prevalent in various real-world applications. Despite the promising results of deep learning models in time series forecasting, especially the Recurrent Neural Networks (RNNs), the explanations…

Time SeriesTime Series Forecasting

Gated Recurrent Neural Tensor Network

2017-06-07 · Andros Tjandra, Sakriani Sakti, Ruli Manurung, Mirna Adriani 외

Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capt…

Language ModelingLanguage Modelling

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

2020-08-21 · Dingheng Wang, Bijiao Wu, Guangshe Zhao, Man Yao 외

Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, since the modern RNNs, including long-short term memory (LSTM) a…

Tensor DecompositionVideo Recognition

Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting

2021-05-11 · Yao Lei Xu, Giuseppe G. Calvi, Danilo P. Mandic

Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory. However, when dealing with large dimensional data, the correspond…

Tensor Decomposition