Abstract | ||
---|---|---|
In many applications, a parsimonious model is often preferred for better interpretability and predictive performance. Online algorithms have been studied extensively for building such models in big data and fast evolving environments, with a prominent example, FTRL-proximal [1]. However, existing methods typically do not provide confidence levels, and with the usage of L1 regularization, the model estimation can be undermined by the uniform shrinkage on both relevant and irrelevant features. To address these issues, we developed OLSS, a Bayesian online sparse learning algorithm based on the spike-and-slab prior. OLSS achieves the same scalability as FTRL-proximal, but realizes appealing selective shrinkage and produces rich uncertainty information, such as posterior inclusion probabilities and feature weight variances. On the tasks of text classification and click-through-rate (CTR) prediction for Yahoo!'s display and search advertisement platforms, OLSS often demonstrates superior predictive performance to the state-of-the-art methods in industry, including Vowpal Wabbit [2] and FTRL-proximal. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICDM50108.2020.00023 | 2020 IEEE International Conference on Data Mining (ICDM) |
Keywords | DocType | ISSN |
Sparse learning,Bayesian | Conference | 1550-4786 |
ISBN | Citations | PageRank |
978-1-7281-8317-6 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shikai Fang | 1 | 0 | 0.68 |
Shandian Zhe | 2 | 50 | 18.41 |
Kuang-Chih Lee | 3 | 35 | 6.44 |
Kai Zhang | 4 | 588 | 32.87 |
Jennifer Neville | 5 | 2092 | 117.45 |