Home
Background
I'm currently an Applied Scientist at Amazon AI. I obtained my PhD in Machine Learning, under Prof. Claire Monteleoni, from The George Washington University, where I also earned my B.S. in Mathematics.
For detailed information, please see my Curriculum Vitae
In preparation
ReLu-activated auto-encoders learn sparsely used dictionaries with weight-normalized SGD
Cheng Tang, Claire Monteleoni, in preparation, 2019.
Publications
Cheng Tang, Andrew Arnold. Neural document expansion for ad-hoc information retrieval. Submitted. 2020.
Cheng Tang. Exponentially convergent stochastic k-PCA without variance reduction. Accepted as (oral @ NeurIPS 2019 , 0.5% acceptance rate).
Cheng Tang, Damien Garreau, Ulrike von Luxburg. When do random forests fail? In proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018).
Cheng Tang, Claire Monteleoni. Convergence rate of stochastic k-means. In proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017).
[Latest version on arXiv] [AISTATS proceedings version] [Code for experiments]
Cheng Tang, Claire Monteleoni. On Lloyd's algorithm: new theoretical insights for clustering in practice. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016).
Cheng Tang, Claire Monteleoni. Scalable constant k-means approximation via heuristics on well-clusterable data. NIPS workshop on Learning faster with easy data II, 2015.
Cheng Tang, Claire Monteleoni. Detecting extreme events from climate time-series via topic modeling. In Machine Learning and Data Mining Approaches to Climate Science: Proceedings of the 4th International Workshop on Climate Informatics. Lakshmanan, V. Gilleland, E. McGovern, A. Tingley, M. (Eds.), Springer, 2015.
This work was featured as "Can topic modeling shed light on climate extremes?" In IEEE Computing in Science and Engineering (CISE) Magazine, Special Issue on Computing & Climate. Vol. 17, no. 6, pp. 43-52, Nov./Dec. 2015.
[IEEE CISE version] [CI workshop proceedings version]
Mahesh Mohan, Cheng Tang, Claire Monteleoni, Tim DeSole, Ben Cash. Seasonal Prediction using unsupervised feature learning and regression. In Proceedings of the 5th International Workshop on Climate Informatics, 2015.
Cheng Tang, Claire Monteleoni. Scaling up Lloyd's algorithm: stochastic and parallel block-wise optimization perspectives. 7th NIPS workshop on optimization for machine learning (OPT2014), 2014.
Cheng Tang, Claire Monteleoni. On the Convergence Rate of Stochastic Gradient Descent for Strongly Convex Functions. International Workshop on Advances in Regularization, Optimization, Kernel methods and Support vector machines (ROKS 2013).