Reservoir Computing meets Recurrent Kernels and Structured Transforms
This work addresses efficiency challenges in Reservoir Computing for time series analysis, offering incremental improvements in speed and memory usage for researchers and practitioners in machine learning.
The paper tackles the problem of improving Reservoir Computing for chaotic time series prediction by establishing a recurrent kernel limit and introducing structured approximations, resulting in methods that are competitive, computationally efficient, and faster with memory savings compared to conventional approaches.
Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained. In the large size limit, such random neural networks have a deep connection with kernel methods. Our contributions are threefold: a) We rigorously establish the recurrent kernel limit of Reservoir Computing and prove its convergence. b) We test our models on chaotic time series prediction, a classic but challenging benchmark in Reservoir Computing, and show how the Recurrent Kernel is competitive and computationally efficient when the number of data points remains moderate. c) When the number of samples is too large, we leverage the success of structured Random Features for kernel approximation by introducing Structured Reservoir Computing. The two proposed methods, Recurrent Kernel and Structured Reservoir Computing, turn out to be much faster and more memory-efficient than conventional Reservoir Computing.