My picture

Contact information

E-mail


Office Address

Microsoft Research
Biological Computation Lab
Health Intelligence

21 Station Rd, CB12FB
Cambridge, UK

Journals   Conferences    Thesis    Talks

Journals

2021

  • Jacobs, M., Pradier, M. F., McCoy, T. H., Perlis, R. H., Doshi-Velez, F., & Gajos, K. Z.How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection. Nature Translational Psychiatry. 2021. [link]

2020

  • M. F. Pradier, T. H. McCoy, M. Hughes, R. H. Perlis and F. Doshi-Velez. Predicting Treatment Discontinuation after Antidepressant Initiation. Nature Translational Psychiatry. 2020. [link]
  • I. Valera, M. F. Pradier, M. Lomeli, and Z. Ghahramani. General Latent Feature Models for Heterogeneous Datasets. Accepted to Journal of Machine Learning Research. 2020.
    [pdf] [code]
  • M. C. Hughes, M. F. Pradier, A. S. Ross, T. H. McCoy, R. H. Perlis and F. Doshi-Velez. Assessment of a Prediction Model for Antidepressant Treatment Stability using Supervised Topic Models. JAMA Network Open. 2020. [link] [medrxiv]

2019

  • M. F. Pradier, M. C. Hughes, T. H. McCoy, S. Barroilhet, F. Doshi-Velez and R. H. Perlis. Predicting Transition from Mayor Depression to Bipolar Disorder after Antidepressant Initiation. In submission to American Journal of Psychiatry. 2019.
  • S. Stark, S. L. Hyland, M. F. Pradier, K. Lehmann, A. Wicki, F. Perez-Cruz, J. E. Vogt, and G. Ratsch. Unsupervised Extraction of Phenotypes from Cancer Clinical Notes for Association Studies. In submission to Nature Communications. 2019. [link]
  • M. F. Pradier, B. Reis, L. Jukofsky, F. Milletti, T. Ohtomo, F. Perez-Cruz, and O. Puig. Case-control Indian Buffet Process identifies biomarkers of response to Codrituzumab. BMC Cancer. 2019. [pdf]

2018

  • M. F. Pradier*, Z. Utkovski*, V. Stojkoski, L. Kocarev and F. Perez-Cruz. Economic Complexity Unfolded: An Interpretable Model for the Productive Structure of Economies. PlosONE. 2018. [pdf]

2016

  • M. F. Pradier, F. J. R. Ruiz, and F. Perez-Cruz. Prior Design for Dependent Dirichlet Processes: An Application to Marathon Modeling. PlosONE. 2016. [pdf]
  • M. F. Pradier, P. M. Olmos, and F. Perez-Cruz. Entropy-Constrained Scalar Quantization with a Lossy-Compressed Bit. Entropy. 2016. [pdf]

Conferences and Workshops

2020

  • M. Jacobs, J. He, M. F. Pradier, T. H. McCoy, R. H. Perlis, F. Doshi-Velez, K. Z. Gajos. Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens. Submitted to ACM CHI Conference on Human Factors in Computing Systems. 2020.
  • B. Coker, M. F. Pradier, and F. Doshi-Velez. Towards Expressive Priors for Bayesian Neural Networks: Poisson Process Radial Basis Function Networks. Conference on Uncertainty in Artificial Intelligence (UAI). 2020. [link]

2019

  • M. F. Pradier, M. C. Hughes, and F. Doshi-Velez. Challenges in Computing and Optimizing Upper Bounds of Marginal Likelihood based on Chi-Square Divergences. Advances in Approximate Bayesian Inference Workshop (AABI). 2019. [link]
  • M. Jacobs, M. F. Pradier, E. Mynatt, R. H. Perlis, F. Doshi-Velez, and K. Z. Gajos. Integrating AI Recommendations into the Pharmacologic Management of Major Depressive Disorder. ACM Conference on Computer-Supported Cooperative Work and Social Computing (ACM-CSCW). 2019.
  • W. Yang, L. Lorch, M. A. Graule, S. Srinivasan, A. Suresh, J. Yao, M. F. Pradier, and F. Doshi-Velez. Output-Constrained Bayesian Neural Networks. ICML Workshop on Generalization. 2019. [link]
  • M. F. Pradier, S. L. Hyland, S. Stark, K. Lehmann, J. E. Vogt, F. Perez-Cruz, and G. Ratsch. A Bayesian Nonparametric Approach to Discover Clinico-Genetic Associations across Cancer Types. BioArXiv. 2019. [link]

2018

  • M. F. Pradier, W. Pan, M. Yau, R. Singh, and F. Doshi-Velez. Hierarchical Stick-breaking Paintbox. Paper + spotlight at BNP@NeurIPS. Montreal (Canada), December 2018.
    [pdf] [spotlight] [poster]
  • M. F. Pradier, W. Pan, J. Yao, S. Ghosh, and F. Doshi-Velez. Projected BNNs: Avoiding Pathologies in Weight Space by projecting Neural Network Weights. BDL@NeurIPS. Montreal (Canada), December 2018. [pdf] [arxiv] [poster]
  • M. F. Pradier, V. Stojkoski, Z. Utkovski, L. Kocarev, and F. Perez-Cruz. Sparse Three-parameter Restricted Indian Buffet Process for Understanding International Trade. International Conference on Acoustic, Speech, and Signal Processing. Calgary (Canada), April 2018. [pdf] [poster]

2017

  • I. Valera, M. F. Pradier, and Z. Ghahramani. General Latent Feature Modeling for Data Exploration Tasks. Best Paper Award at 2017 ICML Workshop on Human Interpretability in Machine Learning. Sydney (Australia), August 2017. [pdf]

2015

  • M. F. Pradier, and F. Perez-Cruz. Infinite Mixture of Global Gaussian Processes. "Bayesian Non-parametrics: the next generation" Workshop BNP@NIPS. Montreal (Canada), December 2015. [pdf] [supp] [poster]
  • S. Stark, M. F. Pradier, S. Hyland, J. E. Vogt, F. Perez-Cruz and G. Ratsch. Large-Scale Sentence Clustering from Electronic Health Records for Genetic Associations in Cancer. Paper + Spotlight Talk at the "Machine Learning in Computational Biology" Workshop, MLCB@NIPS. Montreal (Canada), December 2015. [pdf] [spotlight] [poster]
  • M. F. Pradier, T. Karaletsos, S. Stark, J. E. Vogt, F. Perez-Cruz and G. Ratsch. Bayesian Poisson Factorization for Genetic Associations with Clinical Features in Cancer. Machine Learning for Healthcare ML4H@NIPS. Montreal (Canada), December 2015.
    [pdf] [talk] [poster]

2014

  • M. F. Pradier, P. G. Moreno, F. J.R. Ruiz, I. Valera, H. Molina-Bulla and F. Perez-Cruz. Map/Reduce Uncollapsed Gibbs Sampling for Bayesian Non Parametric Models. Paper + Spotlight Talk at the "Software Engineering for Machine Learning" Workshop, SE4ML@NIPS. Montreal (CA, USA), December 2014. [pdf] [spotlight] [poster]

Thesis

  • Bayesian nonparametrics for data exploration. September 2017. Best dissertation award ("premio extraordinario de doctorado" granted by University Carlos III) [pdf] [slides]

Selected Talks

  • Are you Exploiting Your Assumptions? Towards Expressive Priors for Biomarker Discovery and Functional Prediction. CS Seminar. Massachusetts Institute of Technology (Cambridge MA, US). February 2020. [slides]
  • Towards Expressive Priors for Bayesian NNs: Poisson Process Radial Basis Function Networks. Data Science Institute, Columbia University (Madrid, Spain). December 2019. [slides]
  • Applications of latent variable models for data exploration and uncertainty quantification. Data Science Institute, Columbia University (New York, United States). June 2019. [slides]
  • Probabilistic modeling for biomedical applications. Center of research for computational health, Massachusetts General Hospital (Cambridge, United States). March 2019.
  • Proj-BNNs: Avoiding weight-space pathologies by projecting neural network weights. IBM Research (Cambridge, United States), November 2018. [slides]
  • CRCS seminar: Bayesian nonparametrics for data exploration. Harvard University (Cambridge, United States). March 2017. [slides]
  • Bayesian nonparametrics for data exploration: An application to international trade. BBVA Data & Analytics (Madrid, Spain), September 2017. [slides]
  • A Bayesian nonparametric approach to understand world economies. Audiovisual Communications Lab in EPFL (Lausanne, Switzerland), March 2017. [slides]
  • Bayesian modeling for biomarker discovery in clinical trials. "Big data in human genetics: opportunities and challenges?" Workshop at European Society of Human Genomics. ESHG 2016 (Barcelona, Spain), May 2016. [slides]
  • Indian Buffet Process for Biomarker Discovery. Roche Innovation Center, (New York, United States), November 2016. [slides]
  • Machine Learning for Personalized Medicine. Gregorio Marañon Health Research Institute, Madrid, Spain. [slides]
  • Bayesian Non-parametrics and Variational Inference: A brief Introduction. Signal Processing Dpt at the Technical University of Madrid. [slides]
  • Probabilistic Analysis of Genetic Associations with Clinical Features in Cancer. Spotlight Talk Award at the Annual Machine Learning Symposium. New York Academy of Sciences (NY, USA), March 2017. [slides]
  • An Introduction to Bayesian Non-Parametrics for Biological Applications. Computational Biology Dpt., Memorial Sloan-Kettering Cancer Center, New York, United States, February 2014. [slides]
  • Sparse Three-parameter Restricted IBP for Understanding International Trade. Contributed Talk at Bayesian Nonparametric Workshop BNP@NIPS (Montreal, Canada), December 2016. [slides]
  • Modeling the productive structure of economies: A nonparametric Bayesian approach. Group Talk. Signal Theory and Processing Group. University Carlos III in Madrid (Spain), September 2016. [slides]
  • Bayesian Non-parametric Modeling for Marathon Age Grading. Group Talk. Signal Theory and Processing Group. University Carlos III in Madrid (Spain), February 2014. [slides]
  • Scalar Quantization with Lossy Binary Coding for Gaussian Sources. Group Talk. Signal Theory and Processing Group. University Carlos III in Madrid (Spain), October 2013. [slides]