Corpus ID: 53112125

Differentiable Greedy Networks

  title={Differentiable Greedy Networks},
  author={T. Powers and Rasool Fakoor and Siamak Shakeri and A. Sethy and Amanjit Kainth and Abdel-rahman Mohamed and R. Sarikaya},
  • T. Powers, Rasool Fakoor, +4 authors R. Sarikaya
  • Published 2018
  • Mathematics, Computer Science
  • ArXiv
  • Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is trainable with gradient-based methods yet achieves near-optimal performance via submodular optimization. We focus on the task of identifying a relevant set of sentences for claim verification in the context of the FEVER task. Conventional methods for this task look at sentences on their individual merit and thus do not… CONTINUE READING
    4 Citations
    Differentiable Greedy Submodular Maximization with Guarantees and Gradient Estimators
    • Highly Influenced
    Differentiable Greedy Submodular Maximization: Guarantees, Gradient Estimators, and Applications
    • Highly Influenced
    • PDF
    Trainable Decoding of Sets of Sequences for Neural Sequence Models
    • 3
    • PDF


    Differentiable Submodular Maximization
    • 19
    • PDF
    Submodular meets Spectral: Greedy Algorithms for Subset Selection, Sparse Approximation and Dictionary Selection
    • 317
    • PDF
    A Class of Submodular Functions for Document Summarization
    • 606
    • PDF
    SFO: A Toolbox for Submodular Function Optimization
    • 93
    • PDF
    Differentiable Dynamic Programming for Structured Prediction and Attention
    • 53
    • PDF
    Large-Margin Learning of Submodular Summarization Models
    • 57
    • PDF
    An analysis of approximations for maximizing submodular set functions—I
    • 3,572
    • PDF
    Learning Mixtures of Submodular Functions for Image Collection Summarization
    • 141
    • PDF
    Fast Constrained Submodular Maximization: Personalized Data Summarization
    • 78
    • PDF
    Adam: A Method for Stochastic Optimization
    • 56,769
    • PDF