1. •MLPACK: A scalable C++ machine learning library

  2. Ryan Curtin, James Cline, Neil Slagle, William March, Parikshit Ram, Nishant Mehta, and Alexander Gray.

  3. arXiv 1210.6293, 2012 (under review at JMLR)

  4. •Sparsity-based generalization bounds for predictive sparse coding

  5. Nishant Mehta and Alexander Gray

  6. To be presented at ICML 2013 (camera-ready imminent)

  7. •  Long version (under review at JMLR): On the sample complexity of predictive sparse coding

  8. arXiv 1202.4050, 2012

  9. •Minimax multi-task learning and a generalized loss-compositional paradigm for MTL

  10. Nishant Mehta, Dongryeol Lee, and Alexander Gray

  11. NIPS 2012

  12. •  Shorter, workshop version: Minimax multi-task learning

  13. NIPS 2012 Workshop on Multi-Trade-offs in Machine Learning

  14. •Computer detection approaches for the identification of phasic electromyographic (EMG) activity during human sleep

  15. Jacqueline Fairley, George Georgoulas, Nishant Mehta, Alexander Gray, and Donald Bliwise

  16. Biomedical Signal Processing and Control, 2012

  17. •Discriminative sparse coding for classification and regression

  18. Nishant Mehta and Alexander Gray

  19. The Learning Workshop (Snowbird), 2011. Oral presentation

  20. •Generative and latent mean map kernels

  21. Nishant Mehta and Alexander Gray

  22. arXiv 1005.0188, 2010

  23. •Recognizing sign language from brain imaging

  24. Nishant Mehta, Thad Starner, Melody Moore Jackson, Karolyn Babalola, and George Andrew James

  25. International Conference on Pattern Recognition (ICPR), 2010

  26. •  Longer, earlier version: Recognizing sign language from brain imaging

  27. GVU Technical Report GIT-GVU-09-06, 2009

  28. •Optimal control strategies for an SSVEP-based brain-computer interface

  29. Nishant Mehta, Sadhir Hussain, and Melody Moore Jackson

  30. International Journal of Human-Computer Interaction, 2010

  31. •FuncICA for time series pattern discovery

  32. Nishant Mehta and Alexander Gray

  33. SIAM Data Mining, 2009. Nominated for best paper award. Selected for oral presentation

  34. •Estimating neural signal dependence using kernels

  35. Nishant Mehta, Alexander Gray, Thad Starner, and Melody Moore Jackson

  36. NIPS 2008 Workshop on Statistical Analysis and Modeling of Response Dependencies in Neural Populations

I am a PhD candidate studying machine learning in Georgia Tech’s College of Computing. My thesis advisor is Alexander Gray (FASTlab); I’ve also worked with Melody Moore Jackson and Thad Starner on brain-computer interfaces.


My research focuses on sparsity, multi-task learning, and learning latent representations using supervised information, with an emphasis on learning theoretic results. This also is the focus of my dissertation, which is to show that it is possible to learn sparse representations well, both empirically and theoretically, using multi-task learning.

Beyond that, I’m interested in new learning frameworks, kernel methods, learning on manifolds, and information geometry.


Over the last year, Krishna and organized a seminar on concentration of measure and empirical processes seminar. Vladimir Koltchinskii is now teaching a very nice seminar along these lines, Tuesdays and Thursdays 12:05 PM - 1:25 PM in Skiles 171.


Papers

Teaching

I have been a teaching assistant for

  1. Advanced Machine Learning (Alexander Gray’s “Computational Data Analysis”)

  2. Machine Learning (Guy Lebanon’s “Computational Data Analysis)

  3. Discrete Algorithms (Alberto Apostolico’s “Computational Science & Engineering Algorithms”)

Nishant Mehta


niche ατ |c|c.ga|tech.ed|u

College of Computing

Georgia Institute of Technology

266 Fifth St NW

Atlanta GA 30332

            cv

Relevant Coursework

Machine Learning and Statistics

  1. Statistical estimation, Machine learning theory, Probabilistic graphical models,

  2. Natural language understanding, Combinatorial methods in density estimation,

  3. Introduction to information theory, Neural coding, Spatial statistics

Algorithms

  1. Design and analysis of algorithms, Spectral algorithms, Bioinformatics algorithms (String algorithms)

Math

  1. Introduction to geometry and topology I and II, Introduction to graph theory

Optimization

  1. Linear optimization, Nonlinear optimization