
Affiliation
Research scientist, Google Research, Brain team, Paris.
Contact
mblondel AT google DOT com (work) or mathieu AT thisdomain DOT org (personal)
Short bio
I obtained my PhD in machine learning from Kobe University, Japan, in 2013. From 2013 to 2019, I was a researcher at NTT Communication Science Laboratories in Kyoto, Japan. I am now a senior research scientist at Google Research, Brain team, in Paris, France.
News
- 2022/09/15: Our papers "Efficient and Modular Implicit Differentiation" and "Learning Energy Networks with Generalized Fenchel-Young Losses" were accepted for publication at NeurIPS 2022.
- 2022/01/18: Our paper "Sinkformers: Transformers with Doubly Stochastic Attention" was accepted for publication at AISTATS 2022.
- 2021/05/08: Our paper "Momentum Residual Neural Networks" was accepted for publication at ICML 2021.
- 2021/01/23: Our paper "Differentiable Divergences Between Time Series" was accepted for publication at AISTATS 2021.
- 2020/09/25: Our paper "Learning with Differentiable Perturbed Optimizers" was accepted for publication at NeurIPS 2020.
- 2020/06/01: Our papers "Fast Differentiable Sorting and Ranking" and "Implicit Differentiation of Lasso-type Models for Hyperparameter Optimization" were accepted for publication at ICML 2020.
- 2019/09/04: My paper "Structured Prediction with Projection Oracles" was accepted for publication at NeurIPS 2019.
- 2019/09/02: I have joined Google Brain in Paris as a research scientist.
- 2019/04/22: Our paper "Geometric Losses for Distributional Learning" was accepted for publication at ICML 2019.
- 2018/12/23: Our paper "Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms" was accepted for publication at AISTATS 2019.
- 2018/05/11: Our papers "Differentiable Dynamic Programming for Structured Prediction and Attention" and "SparseMAP: Differentiable Sparse Structured Inference" were accepted for publication at ICML 2018.
- 2017/12/22: Our paper "Smooth and Sparse Optimal Transport" was accepted for publication at AISTATS 2018.
- 2017/09/05: Our two papers "Multi-output Polynomial Networks and Factorization Machines" and "A Regularized Framework for Sparse and Structured Neural Attention" were accepted for publication at NIPS 2017.
- 2017/05/13: Our paper "Soft-DTW: a Differentiable Loss Function for Time-Series" was accepted for publication at ICML 2017.
- 2016/08/12: Our paper "Higher-order Factorization Machines" was accepted for publication at NIPS 2016.
- 2016/04/25: Our paper "Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms" was accepted for publication at ICML 2016.