Sequential Regression Learning with Randomized Algorithms
By: Dorival Leão, Reiko Aoki, Teh Led Red
Potential Business Impact:
Learns patterns in changing information.
This paper presents ``randomized SINDy", a sequential machine learning algorithm designed for dynamic data that has a time-dependent structure. It employs a probabilistic approach, with its PAC learning property rigorously proven through the mathematical theory of functional analysis. The algorithm dynamically predicts using a learned probability distribution of predictors, updating weights via gradient descent and a proximal algorithm to maintain a valid probability density. Inspired by SINDy (Brunton et al. 2016), it incorporates feature augmentation and Tikhonov regularization. For multivariate normal weights, the proximal step is omitted to focus on parameter estimation. The algorithm's effectiveness is demonstrated through experimental results in regression and binary classification using real-world data.
Similar Papers
Sparse identification of nonlinear dynamics with high accuracy and reliability under noisy conditions for applications to industrial systems
Systems and Control
Predicts complex engine behavior accurately, even with noise.
Sparse Identification of Nonlinear Dynamics with Conformal Prediction
Machine Learning (CS)
Makes computer models more sure about predictions.
Learning from Less: SINDy Surrogates in RL
Machine Learning (CS)
Teaches robots faster with less practice.