Mathieu Blondel

16

Papers

344

Total Citations

Papers (16)

Higher-Order Factorization Machines

NeurIPS 2016arXiv

A Regularized Framework for Sparse and Structured Neural Attention

NeurIPS 2017arXiv

Multi-output Polynomial Networks and Factorization Machines

NeurIPS 2017arXiv

Loss Functions and Operators Generated by f-Divergences

Joint Learning of Energy-based Models and their Partition Function

How do Transformers Perform In-Context Autoregressive Learning ?

Decoding-time Realignment of Language Models

Differentiable Dynamic Programming for Structured Prediction and Attention

SparseMAP: Differentiable Sparse Structured Inference

Geometric Losses for Distributional Learning

Structured Prediction with Projection Oracles

Learning with Differentiable Pertubed Optimizers

Efficient and Modular Implicit Differentiation

Learning Energy Networks with Generalized Fenchel-Young Losses

Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms

Soft-DTW: a Differentiable Loss Function for Time-Series