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

[home]   [research]   [courses]


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.

  • D. Raviv, T. Hazan and M. Osadchy
    Hinge-Minimax Learner for the Ensemble of Hyperplanes
    Journal of Machine Learning Research (JMLR), 2018.
  • H. Averbuch-Elor, J. Kopf, T. Hazan and D. Cohen-Or
    Co-Segmentation for Space-Time Co-located Collections
    The Visual Computer Journal, 2018
  • A. Manos, I. Klein and T. Hazan
    Gravity Direction Estimation and Heading Determination for Pedestrian Navigation.
    International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2018.

  • A. Cohen, T. Hazan and T. Koren
    Tight Bounds for Bandit Combinatorial Optimization
    Computational Learning Theory (COLT), 2017
  • I. Schwartz, A. Schwing and T. Hazan
    High Order Attention Models for Visual Question Answering
    Neural Information Processing Systems (NIPS), 2017
  • O. Plonsky, I. Erez and, T. Hazan and M. Tenenholtz
    Psychological Forest: Predicting Human Behavior
    Association for the Advancement of Artificial Intelligence (AAAI), 2017
  • A. Cohen, T. Hazan and T. Koren
    Online Learning with Feedback Graphs Without the Graphs
    International Conference on Machine Learning (ICML), 2016
  • Y. Tenzer, A. Schwing, K. Gimpel and T. Hazan
    Constraints Based Convex Belief Propagation
    Neural Information Processing Systems (NIPS), 2016
  • T. Galanti, L. Wolf and T. Hazan
    A Theoretical Framework for Deep Transfer Learning
    Information and Inference, 2016
  • T. Hazan, A. Schwing and R. Urtasun
    Blending Learning and Inference in Conditional Random Fields
    Journal of Machine Learning Research (JMLR), 2016.
    [code]
  • J. Kappes, P. Swoboda, B. Savchynskyy, T. Hazan and C. Schnorr
    Multicuts and Perturb and MAP for Probabilistic Graph Clustering
    Journal of Mathematical Imaging and Vision (JMIV), 2016
  • I. Ben Shalom, N. Levy, L. Wolf, N. Dershowitz, A. Ben Shalom, R. Shweka, Y. Choueka, T. Hazan and Y. Bar
    Active Congruency-Based Reranking
    Frontiers in Digital Humanities, 2016
  • T. Hazan and T. Jaakkola
    Steps Toward Deep Kernel Methods from Infinite Neural Networks.
    Preprint.
  • O. Meshi, N. Srebro and T. Hazan
    Efficient training of Structured SVMs via Soft Constraints
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2015.
  • A. Cohen and T. Hazan
    Following the Perturbed Leader for Online Structured Learning
    International Conference of Machine Learning (ICML), 2015.
  • R. Osadchy, T. Hazan and D. Keren.
    K-hyperplane Hinge-Minimax Classifier
    International Conference of Machine Learning (ICML), 2015.
  • J. Kappes, P. Swoboda, B. Savchynskyy, T. Hazan and C. Schnorr
    Probabilistic Correlation Clustering and Image Partitioning using Perturbed Multicut
    International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), 2015.
  • F. Orabona, T. Hazan, A. Sarwate and T. Jaakkola.
    On Measure Concentration of Random Maximum A-Posteriori Perturbations
    International Conference of Machine Learning (ICML), 2014.
  • A. Schwing, T. Hazan, M. Pollefeys and R. Urtasun.
    Globally Convergent Parallel MAP LP Relaxation Solvers using the Frank-Wolfe Algorithm
    International Conference of Machine Learning (ICML), 2014.
  • L. Ben Shalom, A. Ben Shalom, N. Levy, L. Wolf, T. Hazan, N. Dershowitz, Y. Bar, R. Shweka and Y. Choueka.
    Congruency-Based Rereanking
    Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
  • A. Gane, T. Hazan, and T. Jaakkola.
    Learning with Random Maximum A-Posteriori Perturbation Models
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2014.
  • S. Maji, T. Hazan and T. Jaakkola.
    Efficient Boundary Annotation using Random Maximum A-Posteriori Perturbations
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2014.
  • T. Kaser, A. Schwing, T. Hazan and M Gross.
    Computational Education using Latent Structured Prediction
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2014.
  • T. Hazan, S. Maji and T. Jaakkola.
    On Sampling from the Gibbs distribution with Random Maximum A-Posteriori Perturbations
    Neural Information and Processing Systems (NIPS), 2013.
  • T. Hazan, S. Maji. J. Keshet and T. Jaakkola.
    Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions
    Neural Information and Processing Systems (NIPS), 2013.
  • A. Schwing, T. Hazan, M. Pollefeys and R. Urtasun.
    Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins
    Neural Information and Processing Systems (NIPS), 2012.
  • K. Yamaguchi, T. Hazan, D. McAllester and R. Urtasun.
    Continuous Markov Random Fields for Robust Stereo Estimation
    European Conference of Computer Vision (ECCV), 2012.
  • T. Hazan, J. Peng and A. Shashua.
    Tightening Fractional Covering Upper Bounds on the Partition Function for High-Order Region Graphs
    Uncertainty in Artificial Intelligence (UAI), 2012.
  • T. Hazan and T. Jaakkola.
    On the Partition Function and Random Maximum A-Posteriori Perturbations
    International Conference of Machine Learning (ICML), 2012.
    Best papers short list at ICML 2012 Machine Learning best papers track at AAAI 2012
  • A. Schwing, T. Hazan, M. Pollefeys and R. Urtasun.
    Efficient Structured Prediction with Latent Variables for General Graphical Models
    International Conference of Machine Learning (ICML), 2012.
  • A. Schwing, T. Hazan, M. Pollefeys and R. Urtasun.
    Efficient Structured Prediction for 3D Indoor Scene Understanding
    Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
  • J. Peng, T. Hazan, N. Srebro and J. Xu.
    Approximate Inference by Intersecting Semidefinite Bound and Local Polytope
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2012.
  • J. Peng, T. Hazan, D. McAllester and R. Urtasun.
    Convex Max-Product Algorithms for Continuous MRFs with Applications to Protein Folding
    International Conference of Machine Learning (ICML), 2011.
  • A. Schwing, T. Hazan, M. Pollefeys and R. Urtasun.
    Distributed Message Passing for Large Scale Graphical Models
    Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
  • J. Keshet, D. McAllester and T. Hazan.
    PAC-Bayesian Approach for Minimization of Phoneme Error Rate
    International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011.
  • D. McAllester, T. Hazan and J. Keshet.
    Direct Loss Minimization for Structured Prediction
    Neural Information and Processing Systems (NIPS), 2010.
  • T. Hazan and R. Urtasun.
    A Primal-Dual Message-Passing Algorithm for Approximated Large Scale Structured Prediction
    Neural Information and Processing Systems (NIPS), 2010.
  • T. Hazan and A. Shashua.
    Norm-Product Belief Propagation: Primal-Dual Message-Passing for LP-Relaxation and Approximate-Inference
    IEEE Transactions on Information Theory, 2010.
  • T. Hazan and A. Shashua.
    Convergent message-passing algorithms for inference over general graphs with convex free energy
    Conference on Uncertainty in Artificial Intelligence (UAI), 2008.
    Best student paper runner up.
  • T. Hazan, A. Man and A. Shashua.
    A Parallel Decomposition Solver for SVM: Distributed Dual Ascent using Fenchel Duality
    Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
  • T. Hazan, R. Hardoon and A. Shashua.
    pLSA for Sparse Arrays With Tsallis Pseudo-Additive Divergence: Noise Robustness and Algorithm
    International Conference of Computer Vision (ICCV), 2007.
  • L. Wolf, H. Jhuang and T. Hazan.
    Learning Appearance with Low-Rank SVM
    Conference on Computer Vision and Pattern Recognition (CVPR), 2007.
  • A. Shashua, R. Zass and T. Hazan.
    Multi-way Clustering Using Super-symmetric Non-negative Tensor Factorization
    European Conference on Computer Vision (ECCV), 2006.
  • T. Hazan, S. Polak and A. Shashua.
    Sparse Image Coding using a 3D Non-negative Tensor Factorization
    International Conference of Computer Vision (ICCV), 2005.
  • A. Shashua and T. Hazan.
    Non-Negative Tensor Factorization with Applications to Statistics and Computer Vision
    International Conference of Machine Learning (ICML), 2005.
  • A. Shashua and T. Hazan.
    Algebraic Set Kernels with Application to Inference Over Local Image Representations
    Neural Information and Processing Systems (NIPS), 2004.