Vahid Tarokh's Home Page


Contact Information:


Vahid Tarokh
The Rhodes Family Professor of Electrical and Computer Engineering
Bass Connections Endowed Professor
Professor of Mathematics
Professor of Computer Science
Microsoft Data Science Investigator
Rhodes Information Initiative at Duke
327 Gross Hall
140 Science Drive
Durham, NC 27708
U.S.A.
(919) 660-7594
E-mail: vahid (dot) tarokh (at) duke (dot) edu


  • Short Biography

  • Advising Information:


  • Current Students and Postdocs

  • Former Postdoctoral Fellows and Their Positions

  • Former PhD Students and Their Positions

  • Former M.S./M.Eng. Students

  • Undergrad Thesis Students and Summer High School Students Supervised

  • Graduate Students Supervised in Other Capacity

  • Theses Examined

  • My Lab, Open Positions


  • The Signal Processing and Applied Statistics (SPAS) Group (My Lab—Under Construction)

  • Postdoctoral Positions Available at My Lab

  • Information for Perspective Graduate Students

  • Research


    My research is mainly mathematical. We look for mathematical nuggets that may lead to new applications. In other words, We do not necessarily build any systems, but make algorithms/mathematical constructions that may be (in some cases) used in future systems.

    Our current research is pursuing new "mathematical" formulations and approaches to getting the most out of datasets. We invent both new mathematical methodologies, and demonstrate these (by numerical simulations) in various scenarios of interest. Current projects are focused on representation, modeling, inference and prediction from data such as predicting rare events from small amounts of data, formulation and calculation of limits of learning from observations, and robust prediction of a macaque monkey's future actions from its (or from what we have learned from another monkey's) brain waves.

    You need to know and be willing to learn more math if you want join my group. Some members of my group have no electrical engineering or any engineering degrees at all. We have members with backgrounds in astronomy, applied mathematics, pure mathematics, physics, electrical engineering and aero-astro engineering. So in every way, we are diverse! Our typical papers usually include theorems and proofs. But I do not call ourselves "pure mathematicians". That said in some cases, we have invented new pure mathematical results in the past.


  • Some Recent Papers
  • Neuroscience
  • Deep Cross-Subject Mapping of Neural Activity , submitted 2020.
  • Deep Pinsker and James-Stein Neural Networks for Brain-Computer Interfacing , submitted 2020.
  • Dictionary Learning and Sparse Coding-based Denoising for High-Resolution Brain Activation and Functional Connectivity Modeling: A Task fMRI Study , to appear in the IEEE Access 2020.
  • Cross-subject Decoding of Eye Movement Goals from Local Field Potentials , to appear in the Journal of Neural Engineering 2020.
  • Minimax-optimal decoding of movement goals from local field potentials using complex spectral features , Journal of Neural Engineering, 2019
  • Sequential Detection of Regime Changes in Neural Data, IEEE/EMBS Conference on Neural Engineering, 2019
  • Wavelet Shrinkage and Thresholding Based Robust Classification for Brain-Computer Interface , IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.
  • Machine Learning
  • Multimodal Controller for Generative Models , submitted 2020.
  • Learning latent stochastic differential equations with variational auto-encoders" , submitted 2020.
  • Fisher Auto-Encoders , submitted 2020.
  • Projected Latent Markov Chain Monte Carlo: Conditional Inference with Normalizing Flows , submitted 2020.
  • An Interpretable Baseline for Time Series Classification Without Intensive Learning , submitted 2020.
  • A Convergent Accelerated Proximal Gradient with Restart for Nonconvex Optimization , Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2020.
  • Distributed Lossy Image Compression with Recurrent Networks , Proceeding of Data Compression Conference 2020.
  • Gradient Information for Representation and Modeling , Conference on Neural Information Processing System (NeurIPS), 2019.
  • SpiderBoost and Momentum: Faster Variance Reduction Algorithms, Conference on Neural Information Processing System (NeurIPS), 2019.
  • Restricted Recurrent Neural Networks , IEEE International Conference on Big Data, 2019.
  • SGD Converges to Global Minimum in Deep Learning via Star-convex Path , International Conference on Learning Representation, 2019.
  • Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels , Conference on Neural Information Processing System (NeurIPS), 2018.
  • On Optimal Generalizability in Parametric Learning, Conference on Neural Information Processing System (NeurIPS), 2017
  • On Data-Dependent Random Features for Improved Generalization in Supervised Learning, The Thirty-Second AAAI Conference on Artificial Intelligence, 2018
  • Statistics and Modeling
  • Model Linkage Selection for Cooperative Learning , submitted 2020.
  • On Statistical Efficiency in Learning , submitted 2020.
  • Bayesian Model Comparison With the Hyvärinen Score: Computation and Consistency , Journal of the American Statistical Association, 2018

  • Asymptotically Optimal Prediction for Time-Varying Data Generating Processes, IEEE Transactions on Information Theory 2019
  • Model Selection Techniques: An overview , IEEE Signal Processing Magazine, 2018.
  • Bridging AIC and BIC: A New Criterion for Autoregression , IEEE Transactions on Information Theory 2018
  • Signal Processing
  • Multiple Change Point Analysis: Fast Implementation And Strong Consistency, IEEE Transactions on Signal Processing, 2017
  • SLANTS: Sequential Adaptive Nonlinear Modeling of Time Series, IEEE Transactions on Signal Processing, 2017
  • Analysis of Multi-State Autoregressive Models, IEEE Transactions on Signal Processing, 2018
  • On Sequential Elimination Algorithms for Best-Arm Identification in Multi-Armed Bandits, IEEE Transactions on Signal Processing, 2017
  • Evolutionary Spectra Based on the Multitaper Method with Application to Stationarity Test, IEEE Transactions on Signal Processing, 2019
  • Online Learning for Multimodal Data Fusion with Application to Object Recognition, IEEE Transactions on Circuits and Systems II: Express Briefs, 2018.
  • Optimization and Control
  • Prediction in Online Convex Optimization for Parametrizable Objective Functions , IEEE Conference on Decision and Control (CDC 2019).
  • Distributed Online Convex Optimization with Improved Dynamic Regret, IEEE Transactions on Automatic Control, submitted 2019.
  • Convergence of Limited Communication Gradient Methods, IEEE Transactions on Automatic Control, 2017.
  • Communication Complexity of Dual Decomposition Methods for Distributed Resource Allocation Optimization , IEEE Journal of Selected Topics in Signal Processing, 2018.
  • Astronomy
  • Robust interferometric imaging via prior-less phase recovery: redundant spacing calibration with generalized-closure phases, Monthly Notices of Royal Astronomical Society, 2017.
  • Resolving phase ambiguities in the calibration of redundant interferometric arrays: implications for array design , Monthly Notices of Royal Astronomical Society, 2016.
  • Mathematics
  • Pseudo-Wigner Matrices , IEEE Transactions on Information Theory, 2018.
  • Symmetric Pseudo-Random Matrices , IEEE Transactions on Information Theory, 2018.
  • Spectral Distribution of Product of Pseudorandom Matrices Formed From Binary Block Codes , IEEE Transactions on Information Theory, 2013.
  • Spectral Distribution of Random Matrices From Binary Linear Block Codes , IEEE Transactions on Information Theory, 2011.
  • On the Trellis Complexity of the Densest Lattice Packings in $\mathbb{R}^n $ , SIAM Journal of Discrete Math, 1996.
  • A Constraint on The Existence of Simple Torsion-Free Lie Modules , Proceedings of American Mathematical Society, 1995.