Jonathan Huang

	email:	jch1@cs.cmu.edu
	office:	200 Smith Hall
		Robotics Institute
		School of Computer Science
		Carnegie Mellon University
		5000 Forbes Avenue
		Pittsburgh, PA 15213
	office phone:	+412 268 8809
	cell phone:	+650 248 7029

About Me:

I am a fourth year Ph.D. student in Robotics at Carnegie Mellon University. My advisor is Carlos Guestrin and I'm also a part of the SELECT Lab run by Carlos Guestrin and Geoff Gordon. Before coming to CMU, I studied math at Stanford University.

Research Interests

My research goals revolve around developing efficient probabilistic reasoning algorithms. I am currently interested in reasoning with uncertainty over permutations. Permutations appear in a variety of real world problems but present a challenging problem for inference due to the fact that there are n! permutations. I have been using Fourier theoretic methods to develop principled and efficient approximate methods for reasoning with permutations.

Publications

• Inference for Distributions over the Permutation Group ,
  Jonathan Huang, Carlos Guestrin, and Leonidas Guibas.
  Tech. Report (CMU-ML-08-108), Machine Learning Department, CMU, 2008.
  [pdf]
  
• Efficient Inference for Distributions on Permutations ,
  Jonathan Huang, Carlos Guestrin, and Leonidas Guibas.
  In Advances in Neural Information Processing Systems (NIPS 2007) ,
  Vancouver, Canada, December 2007.
  Honorable Mention for Outstanding Student Paper.
  [pdf] [slides] [poster] [spotlight] [talk]
  
• A Database of Vocal Tract Resonance Trajectories for Research in Speech Processing ,
  Li Deng , Xiaodong Cui, Robert Pruvenok, Jonathan Huang, Safiyy Momen, Yanyi Chen, Abeer Alwan .
  In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing , May 14-19, 2006, Toulouse, France, pp. 60-63
  [pdf] [poster]

Teaching

• 16-831 (Statistical Techniques in Robotics), Fall '07
• 10-701 (Graduate Machine Learning), Spring '07

Code

• Littlewood-Richardson rule
  Jonathan Huang
  A matlab implementation of the Littlewood-Richardson rule.
  
  • enumeratelrtabs.m
  • lrtabvis.m
• (LDA) Latent Dirichlet Allocation
  Jonathan Huang and Tomasz Malisiewicz,
  An implementation of the mean field inference/learning algorithms from Blei et al. (2003)
  
  • ldainference.m
  • lda_param_est.m
  • trainLDA.m
  Sample output on 20 Newsgroups dataset: [Link]
• Matlab function for visualizing a 2d Dirichlet distribution,
  Jonathan Huang
• HLNfit,
  Jonathan Huang and Tomasz Malisiewicz,
  Code for fitting a Hierarchical Logistic Normal distribution

Data

• Puzzle Data: [View][Download]

Miscellaneous

• Maximum Likelihood Estimation of Dirichlet Distributions ,
  Jonathan Huang,
  Notes on several ways to numerically find the MLE of a Dirichlet Distribution. This was done for a Math Fundamentals for Robotics course taught by Mike Erdmann.
• Sperner's Lemma ,
  Jonathan Huang,
  Some theorems/corollaries of Sperner's Lemma that I collected for a combinatorics class. Sperner is an easy combinatorial fact about labelings on a simplicial complex, but it has several surprising applications in topology and analysis.
• Notes on the Kalman Filter ,
  Jonathan Huang,
  A derivation of the Kalman filter updates.
• Cup Products in Computational Topology ,
  Jonathan Huang,
  Senior Honors Thesis (advisor: Gunnar Carlsson). We show an application of topological persistence to computing invariants related to the cohomology (cup product structure) of a finite simplicial complex.

Personal

• Garden of Weedin' (joint work w/Karl Goodman)

  Most people do not know this about me, but I have gardening on my list of former hobbies.

• I've been getting into photography recently, but I haven't had time to put anything online =/