9 citations · 12 across the 3 of their papers we have counts for
4 papers · 1 filter
Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms
Mathieu Blondel, André F. T. Martins, Vlad Niculae
This paper studies Fenchel-Young losses, a generic way to construct convex loss functions from a regularization function. We analyze their properties in depth, showing that they un…
Differentiable Dynamic Programming for Structured Prediction and Attention
Arthur Mensch, 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 algorit…
Blind Source Separation with Optimal Transport Non-negative Matrix Factorization
Antoine Rolet, Vivien Seguy, Mathieu Blondel +1
Optimal transport as a loss for machine learning optimization problems has recently gained a lot of attention. Building upon recent advances in computational optimal transport, we…
SparseMAP: Differentiable Sparse Structured Inference
Vlad Niculae, André F. T. Martins, Mathieu Blondel +1
Structured prediction requires searching over a combinatorial number of structures. To tackle it, we introduce SparseMAP: a new method for sparse structured inference, and its natu…