Nicholas Johnson
Ph.D. Candidate Department of Computer Science and Engineering
University of Minnesota
njohnson [AT] cs.umn.edu
Learning to Predict blog
Online Portfolio Selection Project

Research

I am a Ph.D. candidate at the University of Minnesota being advised by Arindam Banerjee and Maria Gini. I'm broadly interested in Artificial Intelligence and Machine Learning. In particular, my focus has been on online learning algorithms (full information and bandit settings), convex optimization, adversarial learning models, and recommender systems. The application areas I have worked in are finance (portfolio selection), climate science (forecasting), internet content serving (news article recommendations), and cancer genomics.

Publications

  1. Structured Hedging for Resource Allocations with Leverage
    (To appear) In Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2015).
    Nicholas Johnson, Arindam Banerjee

  2. Online Resource Allocation with Structured Diversification [paper] [slides]
    In Proceedings of the 15th SIAM International Conference on Data Mining (SDM 2015).
    Nicholas Johnson, Arindam Banerjee

  3. SubPatCNV: approximate subspace pattern mining for mapping copy-number variations [paper] [Sourceforge]
    In BMC Bioinformatics, 16:16 2015.
    Nicholas Johnson, Huanan Zhang, Gang Fang, Vipin Kumar, Rui Kuang

  4. Online Portfolio Selection with Group Sparsity [paper] [poster]
    In Proceedings of the 28th Association for the Advancement of Artificial Intelligence Conference (AAAI 2014).
    Puja Das, Nicholas Johnson, Arindam Banerjee

  5. Fast Adaptive Learning in Repeated Stochastic Games by Game Abstraction [paper]
    In Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems Conference (AAMAS 2014).
    Mohamed Elidrisi, Nicholas Johnson, Jacob Crandall, Maria Gini

  6. Online Lazy Updates for Portfolio Selection with Transaction Costs [paper] [poster]
    In Proceedings of the 27th Association for the Advancement of Artificial Intelligence Conference (AAAI 2013).
    Puja Das, Nicholas Johnson, Arindam Banerjee

  7. Approximate subspace pattern mining for mapping copy-number variations [poster]
    In Proceedings of the 3rd ACM Conference on Bioinformatics, Computational Biology and Biomedicine (ACM-BCB 2012).
    Nicholas Johnson, Gang Fang, Rui Kuang

  8. Signed Network Propagation for Detecting Differential Gene Expressions and DNA Copy Number Variations [paper]
    In Proceedings of the 3rd ACM Conference on Bioinformatics, Computational Biology and Biomedicine (ACM-BCB 2012).
    Wei Zhang, Nicholas Johnson, Baolin Wu, Rui Kuang

  9. Fast Learning against Adaptive Adversarial Opponents [paper]
    In Proceedings of the Adaptive and Learning Agents Workshop (AAMAS 2012).
    Mohamed Elidrisi, Nicholas Johnson, Maria Gini

Awards

  1. Computer Science and Engineering Ph.D. Conference Travel Award 2015
    Awarded by: University of Minnesota Computer Science Department

  2. Student Travel Award
    Awarded by: SIAM International Conference on Data Mining 2015

  3. Thank a Teacher Award, Fall 2013
    Awarded by: University of Minnesota Center for Teaching and Learning

  4. Minnesota Student Association Award for Graduate Student Teaching, 2012-2013
    Awarded by: Council of Graduate Students

  5. East Asia and Pacific Summer Institutes for U.S. Graduate Students (EAPSI) Fellowship
    Funded by: National Science Foundation (NSF)
    NSF Award 1311040
    Duration: June 12, 2013 - August 8, 2013
    Principal Investigator: Nicholas Johnson

Education

Teaching