Abstract:
|
Many statistical approaches are not well suited for streaming or big data. As data increasingly takes on these forms, statisticians need to adjust their toolbox of analysis methods. OnlineStats is a Julia package which provides online algorithms for statistical models. Observations are processed one at a time and all algorithms use O(1) memory. OnlineStats uses analytical solutions and stochastic approximation techniques for summary statistics, density estimation, generalized linear models with regularization, and machine learning.
|