I am a Senior Research Scientist in Machine Learning at Spotify in New York. My research interests are in latent variable models, variational inference, empirical Bayes, and causality. I have developed a number of Bayesian machine learning techniques presented at top tier machine learning conferences that are successful on text, recommendation, and mobility data.
Previously, I did my postdoctoral training at Princeton University and Columbia University under the advisory of David Blei. I obtained a PhD in 2014, supervised by Nick Jennings and Alex Rogers on the ORCHID project at the University of Southampton, UK. I have an MSc in Computing (Artificial Intelligence) from Imperial College London, and a BA in Computer Science from Oxford University.
10th Sept 2017: I am again on the organizing committee for the Advances in Approximate Bayesian Inference (AABI) workshop to appear at NIPS 2017. We will be asking for submissions soon.
4th Sept 2017: My paper "An Empirical Bayes Approach to Optimizing Machine Learning Algorithms" has been accepted at NIPS 2017 for a spotlight presentation this December. The paper will be posted on arXiv soon.
8th Aug 2017: I will teach the Machine Learning course as an Adjunct Assistant Professor at Columbia University this Fall semester. Here is my dedicated course web page.
25th Apr 2017: I recently taught at the Data Science Bootcamp, a 5 day intensive course at Columbia University that I co-created with Kriste Krstovski, Francisco Rodriguez Ruiz and Collabotory@Columbia.
9th Dec 2016: Gave a talk about my workshop paper on hyperparameter averaging using Gaussian processes.
9th Dec 2016: I am on the organizing committee for the Advances in Approximate Bayesian Inference (AABI) workshop at NIPS 2016. http://approximateinference.org.
1st Dec 2016: Started as a Research Scientist at Spotify in New York!
Abstract: Many modern data analysis problems involve inferences from streaming data. However, streaming data is not easily amenable to the standard probabilistic modeling approaches, which assume that we condition on finite data. We develop population variational Bayes, a new approach for using Bayesian modeling to analyze streams of data. It approximates a new type of distribution, the population posterior, which combines the notion of a population distribution of the data with Bayesian inference in a probabilistic model. We study our method with latent Dirichlet allocation and Dirichlet process mixtures on several large-scale data sets.
Learning periodic human behaviour models from sparse data for
crowdsourcing aid delivery in developing countries [ bib |
J. McInerney, A. Rogers, and N. R. Jennings. In Conference on Uncertainty in Artificial Intelligence (UAI), 2013.
Abstract: In many developing countries, half the population lives in rural locations, where access to essentials such as school materials, mosquito nets, and medical supplies is restricted. We propose an alternative method of distribution (to standard road delivery) in which the existing mobility habits of a local population are leveraged to deliver aid, which raises two technical challenges in the areas optimisation and learning. For optimisation, a standard Markov decision process applied to this problem is intractable, so we provide an exact formulation that takes advantage of the periodicities in human location behaviour. To learn such behaviour models from sparse data (i.e., cell tower observations), we develop a Bayesian model of human mobility. Using real cell tower data of the mobility behaviour of 50,000 individuals in Ivory Coast, we find that our model outperforms the state of the art approaches in mobility prediction by at least 25% (in held-out data likelihood). Furthermore, when incorporating mobility prediction with our MDP approach, we find a 81.3% reduction in total delivery time versus routine planning that minimises just the number of participants in the solution path.
Breaking the habit: measuring and predicting departures from
routine in individual human mobility [ bib |
J. McInerney, S. Stein, A Rogers, and N. R. Jennings. Pervasive and Mobile Computing, 2013.
Abstract: Researchers studying daily life mobility patterns have recently shown that humans are typically highly predictable in their movements. However, no existing work has examined the boundaries of this predictability, where human behaviour transitions temporarily from routine patterns to highly unpredictable states. To address this shortcoming, we tackle two interrelated challenges. First, we develop a novel information-theoretic metric, called instantaneous entropy, to analyse an individual's mobility patterns and identify temporary departures from routine. Second, to predict such departures in the future, we propose the first Bayesian framework that explicitly models breaks from routine, showing that it outperforms current state-of-the-art predictors.
Modelling heterogeneous location habits in human populations for
location prediction under data sparsity [ bib |
J. McInerney, J. Zheng, A. Rogers, and N. R. Jennings. In International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), 2013.
Abstract: In recent years, researchers have sought to capture the daily life location behaviour of groups of people for exploratory, inference, and predictive purposes. However, development of such approaches has been limited by the requirement of personal semantic labels for locations or social/spatial overlap between individuals in the group. To address this shortcoming, we present a Bayesian model of mobility in populations (i.e., groups without spatial or social interconnections) that is not subject to any of these requirements. The model intelligently shares temporal parameters between people, but keeps the spatial parameters specific to individuals. To illustrate the advantages of population modelling, we apply our model to the difficult problem of overcoming data sparsity in location prediction systems, using the Nokia dataset comprising 38 individuals, and find a factor of 2.4 improvement in location prediction performance against a state-of-the-art model when training on only 20 hours of observations.
J. McInerney. An empirical Bayes approach to optimizing machine learning algorithms. In Neural Information Processing Systems (NIPS), Dec 2017. [ pdf ]
J. Guerra, J. Uddin, D. Nilsen, J. Mclnerney, A. Fadoo, I. B. Omofuma, S. Agrawal, P. Allen, H. M. Schambra. Capture, learning, and classification of upper extremity movement primitives in healthy controls and stroke patients. In International Conference on Rehabilitation Robotics (ICORR). Jul 2017. [ pdf ]
J. McInerney and D. Blei. Discovering newsworthy tweets with a geographical topic model. In Workshop on Data Science for News Publishing, in conjunction with Conference on Knowledge Discovery and Data Mining (KDD), July 2014. [ bib | pdf ]
J. McInerney, J. Zheng, A. Rogers, and N. R. Jennings. Modelling heterogeneous location habits in human populations for location prediction under data sparsity. In International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), September 2013. [ bib | pdf ]
A. Rutherford, M. Cebrian, I. Rahwan, S. Dsouza, J. McInerney, V. Naroditskiy, M. Venanzi, N. R. Jennings, J. R. deLara, E. Wahlstedt, and S. U. Miller. Targeted social mobilization in a global manhunt. PLoS ONE, 8(9):e74628, September 2013. [ bib | pdf ]
J. McInerney, S. Stein, A Rogers, and N. R. Jennings. Breaking the habit: measuring and predicting departures from routine in individual human mobility. Pervasive and Mobile Computing, 9(6):808-822, July 2013. [ bib | pdf ]
J. McInerney, A. Rogers, and N. R. Jennings. Learning periodic human behaviour models from sparse data for crowdsourcing aid delivery in developing countries. In Conference on Uncertainty in Artificial Intelligence (UAI), pages 401-410, July 2013. [ bib | pdf ]
I. Rahwan, S. Dsouza, A. Rutherford, V. Naroditskiy, J. McInerney, M. Venanzi, N. R. Jennings, and M. Cebrian. Global manhunt pushes the limits of social mobilization. IEEE Computer, 46(4):68-75, April 2013. [ bib | pdf ]
N. Cuong Truong, J. McInerney, L. Tran-Thanh, E. Costanza, and S. D. Ramchurn. Forecasting multi-appliance usage for smart home energy management. In 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), April 2013. [ bib | pdf ]
J. McInerney, A. Rogers, and N. R. Jennings. Improving location prediction services for new users with probabilistic latent semantic analysis. In 4th International Workshop on Location-Based Social Networks, September 2012. [ bib | pdf ]
[ vbihmm ] Variational inference for hierarichcal HMMs and/or mixture models in Python with customisable and composable observation likelihoods.
(In reverse chronological order)
NIPS Spotlight Talk, Long Beach, California, US - December 2017
NIPS Workshop on Approximate Bayesian Inference (AABI), Barcelona, Spain - December 2016
Probabilistic Programming and Advanced Machine Learning (PPAML) DARPA meeting, Portland, Oregon, US - July 2015
Department of Engineering, Oxford University, Oxford, UK - March 2015
Big Data Workshop, Fields Institute, Toronto, Canada - Jan 2015
Google DeepMind, London, UK - Nov 2014
Machine Learning Group, Cambridge University, Cambridge, UK - Nov 2014
School of Computer Science, Birmingham University, Birmingham, UK - May 2014
International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), Zurich, Switzerland, US - Sept 2013
Placed Inc., Seattle, Washington, US - July 2013
Conference on Uncertainty in Artificial Intelligence (UAI), Bellevue, Washington, US - July 2013
Conference on the Analysis of Mobile Phone Datasets (NetMob), Boston, Massachusetts, US - May 2013
Advanced Technology Centre (ATC), BAE Systems plc, Filton, UK - Feb 2013
International Workshop on Location-Based Social Networks (LBSN), Pittsburgh, Pennsylvania, US - Sept 2012
Mobile Data Challenge by Nokia Workshop, Newcastle, UK - June 2012
Department of Electronics and Computer Science, Politecnico di Milano, Milan, Italy - Dec 2011