Jiantao Jiao


Jiantao Jiao is a Ph.D. student in the Department of Electrical Engineering at Stanford University, advised by Prof. Tsachy Weissman. He received the B.Eng. degree in Electronic Engineering from Tsinghua University, Beijing, China in 2012, and the M.Sc. degree in Electrical Engineering from Stanford University in 2014. He is a recipient of the Presidential Award of Tsinghua University and the Stanford Graduate Fellowship. He was a semi-plenary speaker at ISIT 2015 and a co-recipient of the ISITA 2016 Student Paper Award. He co-designed and co-taught the graduate course EE378A (Statistical Signal Processing) at Stanford University in 2016 and 2017 with his advisor. His research interests are in statistical machine learning, high-dimensional and nonparametric statistics, and information theory, and their applications in medical imaging, genomics, and natural language processing. He is a co-founder of Qingfan, an online platform that democratizes technical training and job opportunities for anyone with access to the internet.

Research Interests

With massively accumulating haystacks of data waiting to be explored for needles of new discoveries, the need for adaptive and computationally efficient algorithms that can fully exploit the samples collected is paramount. Such algorithms are particularly crucial when operating in the high-dimensional and nonparametric inference regimes permeating machine learning and related fields. My work draws on, develops and applies tools from such fields as information theory, probability theory, and approximation theory, with applications in the data sciences at large.


  • Nov 2017: Talk at MIT

  • Nov 2017: Talk at UC Berkeley

  • Oct 2017: Talk at UW-Madison

  • Oct 2017: The code for approximate profile maximum likelihood (APML) released Code Website

  • Oct 2017: Talk at the FOCS 2017 Workshop on Frontiers in Distribution Testing Talk Slides

  • Oct 2017: Talk at Stanford

  • Oct 2017: Talk at Allerton

  • July 2017: Talk at Yale

  • Spring 2017: I am co-teaching EE378A again with my advisor. We demonstrate how to utilize information theoretic methods in machine learning, discuss recent results in functional estimation, reveal the phenomenon of estimating fundamental limits is easier than achieving fundamental limits, demonstrate the underlying mathematics for the general phenomenon of effective sample size enlargement in functional estimation, and introduce Peetre's K-functional and related approximation theoretic quantities to help with statistical analysis. We treat the denoising problem from both learning and decision theoretic perspectives and investigate their relative strengthes. We also cover general Bayes and minimax decision theory, learning theory, and selected algorithms induced by the theory that have been widely deployed in practice.

  • Jan 2017: The Han–Jiao–Weissman (HJW) Kullback–Leibler (KL) divergence estimator released Code website

  • Jan 2017: The version 3.0 Jiao-Venkat-Han-Weissman (JVHW) entropy, Renyi entropy, and mutual information estimators released Code website

  • 2016: In Spring 2016 I am co-teaching EE378A with my advisor. This year's EE378A offering has been substantially revised to reflect modern advances in the mathematics of information processing, as well as detailed comparison and analysis of existing frameworks for data analysis.

  • 2016: Our paper ‘‘Minimax Rate-optimal Estimation of KL Divergence between Discrete Distributions’’ wins the Student Paper Award at ISITA 2016

  • 2016: Our paper ‘‘Minimax Estimation of the L_1 Distance’’ is in the Finalist for the Jack Keil Wolf Student Paper Awards at ISIT 2016

  • June 2015: Our paper ‘‘Maximum Likelihood Estimation of Information Measures’’ is in the semi-plenary sessions of ISIT 2015

  • March, 2015: My talk at the Workshop on Information Theory, Learning and Big Data at the Simons Institute for Theory of Computing

  • 2012: The Matlab code for universal estimation of directed information released Code website


  • Ph.D. Candidate, Department of Electrical Engineering, Stanford University, Jan. 2013 - Present

  • M.Sc., Department of Electrical Engineering, Stanford University, Sept. 2012 - June 2014

  • B.E., Department of Electronic Engineering, Tsinghua University, Beijing, China, August 2008 - July 2012

Professional Activities

  • Reviewer for IEEE Transactions on Information Theory, IEEE Transactions on Signal Processing, IEEE Transactions on Signal and Information Processing over Networks, Entropy, IEEE Statistical Signal Processing Workshop (SSP), Conference on Learning Theory (COLT), International Symposium on Information Theory (ISIT), IEEE Information Theory Workshop (ITW), Symposium on Discrete Algorithms (SODA)


Email: jiantao [at] stanford [dot] edu

Packard Building, Room No. 251
350 Serra Mall
Stanford, CA 9430