online learning

Parallel-and-Stream Accelerator for Computationally Fast Supervised Learning (submitted)

Two dominant distributed computing strategies have emerged to overcome the computational bottleneck of supervised learning with big data: parallel data processing in the MapReduce paradigm and serial data processing in the online streaming paradigm. …


MORA is a real-time regression analysis method that incorporates both dynamics and inter-data batch correlation.


A hybrid paradigm that integrates online streaming processing into each parallelized data process in a MapReduce framework.

Renewable Estimation and Incremental Inference in Generalized Linear Models with Streaming Datasets

This paper presents an incremental updating algorithm to analyze streaming datasets using generalized linear models. The proposed method is formulated within a new framework of renewable estimation and incremental inference, in which the estimates …


A new framework of real-time estimation and incremental inference in generalized linear models (GLMs) with cross-sectional data streams.