Alex Tank


About Me

I am a 5th year Ph.D. student at the Department of Statistics at the University of Washington. I am advised by Emily Fox and am a member of the MODE Lab. I am fortunate to be funded by an IGERT fellowship in Big Data and Data Science.

My research interests are in 1) statistical machine learning approaches to multivariate time series and 2) scalable computation for rich probabilistic models.

CV

Email: alextank at uw dot edu

Watch a talk by my advisor on our work on interpretable neural network models for Granger causality discovery and two talks I gave at KDD 2016 on multivariate categorical time series and subsampled structural VAR models.


Submitted and Working Papers

  • Neural Granger Causality for Nonlinear Time Series, Alex Tank, Ian Covert, Nicholas J. Foti, Ali Shojaie, Emily B. Fox, 2017
  • A Unified Framework for Long Range and Cold Start Forecasting of Seasonal Profiles in Time Series , Chris Xie, Alex Tank, Alec Greaves-Tunell, Emily Fox, 2017
  • Identifiability and Estimation of Structural Vector Autoregressive Models for Subsampled and Mixed Frequency Time Series, Alex Tank, Emily Fox, Ali Shojaie, 2017
  • Granger Causality for Categorical Time Series, Alex Tank, Emily Fox, Ali Shojaie, 2017 (JSM 2018 best student paper award in Business and Economic Statistics)
  • Publications

  • An Efficient ADMM Algorithm for Structural Break Detection in Multivariate Time Series Alex Tank, Emily Fox, Ali Shojaie, NIPS Time Series Workshop Long Beach, CA 2017 (winner of best oral presentation)
  • An Interpretable and Sparse Neural Network Model for Nonlinear Granger Causality Discovery Alex Tank, Ian Covert, Nick Foti, Ali Shojaie, Emily Fox, NIPS Time Series Workshop Long Beach, CA 2017
  • A Unified Framework for Missing Data and Cold Start Prediction for Time Series Data, Chris Xie, Alex Tank, Emily Fox NIPS Time Series Workshop, Barcelona, Spain 2016.
  • Granger Causality Networks for Categorical Time Series Alex Tank, Emily Fox, Ali Shojaie, KDD Time Series Workshop, San Francisco, CA 2016.
  • Identifiability of Non-Gaussian Structural VAR Models for Subsampled and Mixed Frequency Time Series Alex Tank, Emily Fox, Ali Shojaie, KDD Workshop on Causal Discovery, San Francisco, CA, 2016.
  • Bayesian Structure Learning for Stationary Time Series Alex Tank, Nick Foti, Emily Fox, Proceedings of the 31st International Conference on Uncertainty in Artificial Intelligence (UAI) , Amsterdam, Netherlands July 2015.
  • Streaming Variational Inference for Bayesian Nonparametric Mixture Models Alex Tank, Nick Foti, Emily Fox, International Conference on Artificial Intelligence and Statistics (AISTATS) , San Diego, CA 2015.
  • Streaming Variational Inference for Normalised Random Measure Mixture Models Alex Tank, Nick Foti, Emily Fox, NIPS Workshop Advances in Variational Inference Montreal, Canada, 2014