Hassan Ashtiani

Assistant Professor
Department of Computing and Software
Faculty of Engineering
McMaster University

Email: zokaeiam@mcmaster.ca
Phone: +1-905-525-9140 ext. 27234
Office: ITB 246
[Publications] [CV]


My research interests revolve around Machine Learning, Artificial Intelligence, Statistics, and Theoretical Computer Science. In particular, I am interested in formulating new/emerging learning scenarios (including various forms of unsupervised learning), and providing provably efficient methods -- or establishing the inherent limitations -- for solving them.

Some of the directions that I currently work on are
  • Statistically/Computationally Efficient Learning/Testing of Distributions
  • Model Selection for Clustering
  • Provably Efficient Clustering
  • Efficient Learning from High-dimensional Data

  • Updates

    • (Dec. 2018) Our paper on sample complexity of learning mixtures of Gaussians received a Best Paper Award in NeurIPS (NIPS).
    • I am looking for motivated graduate students who are interested to work on the theoretical aspects of machine learning.
    • (Sept. 2018) I joined the Department of Computing and Software, McMaster University.
    • (May 2018) I defended my Ph.D. dissertation.
    • (Feb. 2018) I became a postgraduate affiliate at Vector Institute.

    Highlighted Publications [Full List]

    1. Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes [paper]
      Hassan Ashtiani, Shai Ben-David, Nick Harvey, Chris Liaw, Abbas Mehrabian, Yaniv Plan
      NeurIPS (NIPS) 2018, Oral Presentation (Best Paper Award)

    2. Sample-Efficient Learning of Mixtures [paper]
      Hassan Ashtiani, Shai Ben-David, Abbas Mehrabian
      AAAI 2018

    3. Clustering with Same-Cluster Queries [paper, slides, video]
      Hassan Ashtiani, Shrinu Kushagra, Shai Ben-David
      NIPS 2016, Oral Presenattion

    4. A Dimension-Independent Generalization Bound for Kernel Supervised Principal Component Analysis [paper]
      Hassan Ashtiani, Ali Ghodsi
      JMLR Workshop and Conference Proceedings, Volume 44: NIPS Workshop on Feature Extraction: Modern Questions and Challenges, 2015

    5. Representation Learning for Clustering: A Statistical Framework [paper, poster, presentation]
      Hassan Ashtiani, Shai Ben-David
      UAI 2015, Oral Presnetation