Differentiable Dynamic Programming for Structured Prediction and Attention

  title={Differentiable Dynamic Programming for Structured Prediction and Attention},
  author={Arthur Mensch and Mathieu Blondel},
Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 509 times over the past 90 days. VIEW TWEETS
3 Citations
32 References
Similar Papers

Similar Papers

Loading similar papers…