PBODL : Parallel Bayesian Online Deep Learning for Click-Through Rate Prediction in Tencent Advertising System
Liu, Xun; Xue, Wei; Xiao, Lei; Zhang, Bo;
Subject: Computer Science - Learning
We describe a parallel bayesian online deep learning framework (PBODL) for click-through rate (CTR) prediction within today's Tencent advertising system, which provides quick and accurate learning of user preferences. We first explain the framework with a deep probit re... View more
A. Graves, A.-r. Mohamed and Hinton, G. Speech recognition with deep recurrent neural networks. In A. Krizhevsky, I. Sutskever and Hinton, G. E. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.
Broderick, Tamara, Boyd Nicholas Wibisono Andre Wilson Ashia C and Jordan, Michael. Streaming variational bayes. In NIPS, 2013.
David Stern, Ralf Herbrich, Thore Graepel. Matchbox: Large scale online bayesian recommendations. In WWW, 2009.
G Andrew, J Gao. Scalable training of l1-regularized log-linear models. In ICML, 2007.
H. B. McMahan, G. Holt, D. Sculley M. Young D. Ebner J. Grady L. Nie T. Phillips E. Davydov D. Golovin S. Chikkerur D. Liu M. Wattenberg A. M. Hrafnkelsson T. Boulos and Kubica, J. Ad click prediction: a view from the trenches. In KDD, 2013.
Herna ndez Lobato, J M and Adams, R P. Probabilistic backpropagation for scalable learning of bayesian neural networks. In ICML, 2015.
Lin, Y JuanY ZhuangWS ChinCJ. Field-aware factorization machines for ctr prediction. In RecSys, 2016.
M. Richardson, E. Dominowska. Predicting clicks: estimating the click-through rate for new ads. In WWW, pp. 521-530, 2007.
Minka, Thomas. A family of algorithms for approximate Bayesian inference. PhD thesis, MIT, 2001.