NIPS Proceedingsβ

Tamir Hazan

9 Papers

  • Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder (2019)
  • High-Order Attention Models for Visual Question Answering (2017)
  • Constraints Based Convex Belief Propagation (2016)
  • Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions (2013)
  • On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations (2013)
  • Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins (2012)
  • A Primal-Dual Message-Passing Algorithm for Approximated Large Scale Structured Prediction (2010)
  • Direct Loss Minimization for Structured Prediction (2010)
  • Algebraic Set Kernels with Application to Inference Over Local Image Representations (2004)