Tamir Hazan, Ph.D.
Assistant professor

Faculty of Industrial Engineering and Management
Technion - Israel Institute of Technology
Bloomfield building, room 503
Technion City, Haifa 32000
tamir.hazan at technion.ac.il

[research]   [papers]   [courses]


Research interests

Our research interests involve the theoretical and practical aspects of machine learning. Our research focuses on mathematically founded solutions to modern real life problems that demonstrate non-traditional statistical behavior. Recent examples include efficient learning of high dimensional statistics using Gumbel-max perturbation mdoels in discriminative learning, generative learning and reinforcement learning. We also learn graph based attention models across modalities and consider different aspects of Bayesian deep learning using Gaussian perturbations of their parameters. The practice of our work is motivated by many visual and language problems.

Students

Alex Schwing, now asisstant professor at UIUC.
Alon Cohen, (Ph.D. student)
Idan Schwartz, (Ph.D. student)
Sergey Voldman, (Ph.D. student)
Guy Lorberbom, (M.Sc. studen)
Adi Manos, (M.Sc. student)
Ram Yazdi, (M.Sc. student)
Chana Ross, (M.Sc. student)
Noam Heimann, (M.Sc. student)
Hedda Cohen, (M.Sc. student)
Bar Mayo, (M.Sc. student)

Edited Volumes

Perturbations, Optimization, and Statistics (2016)
Tamir Hazan, George Papandreou, Daniel Tarlow (Editors).
Neural Information Processing series, MIT Press.
[MIT Press], [amazon]

Recent papers

  • T. Hazan, F. Orabona, A. Sarwate, S. Maji and T. Jaakkola
    High Dimensional Inference with Random Maximum A-Posteriori Perturbations
    IEEE Transactions on Information Theory, 2019.

  • G. Lorberbom, A. Gane, T. Jaakkola and T. Hazan.
    Direct Optimization through arg max for Discrete Variational Auto-Encoder
    Preprint.
  • G. Lorberbom, C.Maddison, N. Heess, T. Hazan and D. Tarlow.
    Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
    Preprint.
  • A. Doitch, R. Yazdi, T. Hazan and R. Reichart.
    Perturbation Based Learning for Structured NLP Tasks with Application to Dependency Parsing
    Preprint.
  • I. Schwartz, A. Schwing and T. Hazan
    A Simple Baseline for Audio-Visual Scene-Aware Dialog
    Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

  • I. Schwartz, S. Yu, T. Hazan and A. Schwing
    Factor Graph Attention
    Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

  • T. Galanti, L. Wolf and T. Hazan
    A Formal Approach to Explainability.
    Artificial Intelligence, Ethics, and Society (AIES), 2019.

  • A. Manos, I. Klein and T. Hazan
    Gravity-Based Methods for Heading Computation in Pedestrian Dead Reckoning.
    Sensors, 2019.