Selected Peer-Reviewed Publications:

Machine Learning for Healthcare

  • H Soleimani, J Hensman, S Saria, "Scalable Joint Models for Reliable Uncertainty-Aware Event Prediction'', IEEE Transactions on Pattern Analysis and Machine Intelligence, accepted for publication, 2017,  DOI: 10.1109/TPAMI.2017.2742504. [pdf]
  • H Soleimani*, A Subbaswamy*, S Saria, "Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions, in Proc. Uncertainty in Artificial Intelligence (UAI), 2017.  [pdf, supplement]
    * equal contribution.

Multi-Instance Learning

  • H Soleimani, D J Miller, "Semi-Supervised Multi-Label Multi-Instance Learning for Structured Data", Neural Computation, vol. 29, no. 4, pp. 1053-1102, 2017. [code
  • H Soleimani, D J Miller, "Semi-supervised multi-label topic models for document classification and sentence labeling," In CIKM, pages 105-114, 2016. [code] (acceptance rate: 23%)

Anomaly Detection

  • H Soleimani, D J Miller, “ATD: Anomalous Topic Discovery in High Dimensional Discrete Data”, IEEE Transactions on Knowledge and Data Engineering, vol. 28, no. 9, pp. 2267-2280, 2016, DOI: 10.1109/TKDE.2016.2561288. [preprint, code] Best poster award in ICML 2016 Anomaly Detection Workshop

Topic Models - Hierarchical Graphical Models

  • H Soleimani, D J Miller, “Parsimonious Topic Models with Salient Word Discovery”, IEEE Transactions on Knowledge and Data Engineering, vol. 27, pp. 824-837, 2015. [preprint, code]
  • H Soleimani, D J Miller, “Exploiting the Value of Class Labels in Topic Models for Semi-Supervised Document Classification”, IJCNN, 2016. [code]

Technical Reports and Tutorials:
  • Review of some Bayesian non-parametric models.[IPython Notebook]
  • H Soleimani, “A Comparison of Variational Bayes and Markov Chain Monte Carlo Methods for Topic Models”, Course Project for STAT540: Computationally Intensive Statistical Inference. [pdfcode]