Mathieu Blondel

Implicit Diffusion: Efficient optimization through stochastic sampling AISTATS 2025 Joint Learning of Energy-based Models and their Partition Function ICML 2025 Loss Functions and Operators Generated by f-Divergences ICML 2025 On Teacher Hacking in Language Model Distillation ICML 2025 Decoding-time Realignment of Language Models ICML 2024 How do Transformers Perform In-Context Autoregressive Learning ? ICML 2024 Learning with Fitzpatrick Losses NeurIPS 2024 Stepping on the Edge: Curvature Aware Learning Rate Tuners NeurIPS 2024 Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective ICML 2023 Sparsity-Constrained Optimal Transport ICLR 2023 Efficient and Modular Implicit Differentiation NeurIPS 2022 Implicit Differentiation for Fast Hyperparameter Selection in Non-Smooth Convex Learning JMLR 2022 Learning Energy Networks with Generalized Fenchel-Young Losses NeurIPS 2022 Sinkformers: Transformers with Doubly Stochastic Attention AISTATS 2022 Sparse Continuous Distributions and Fenchel-Young Losses JMLR 2022 Differentiable Divergences Between Time Series AISTATS 2021 Momentum Residual Neural Networks ICML 2021 Fast Differentiable Sorting and Ranking ICML 2020 Implicit differentiation of Lasso-type models for hyperparameter optimization ICML 2020 Learning with Differentiable Pertubed Optimizers NeurIPS 2020 Learning with Fenchel-Young losses JMLR 2020 Geometric Losses for Distributional Learning ICML 2019 Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms AISTATS 2019 Structured Prediction with Projection Oracles NeurIPS 2019 Differentiable Dynamic Programming for Structured Prediction and Attention ICML 2018 Large Scale Optimal Transport and Mapping Estimation ICLR 2018 Smooth and Sparse Optimal Transport AISTATS 2018 SparseMAP: Differentiable Sparse Structured Inference ICML 2018 A Regularized Framework for Sparse and Structured Neural Attention NeurIPS 2017 Multi-output Polynomial Networks and Factorization Machines NeurIPS 2017 Soft-DTW: a Differentiable Loss Function for Time-Series ICML 2017 SVD-Based Screening for the Graphical Lasso IJCAI 2017 Higher-Order Factorization Machines NeurIPS 2016 Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms ICML 2016 Online Passive-Aggressive Algorithms for Non-Negative Matrix Factorization and Completion AISTATS 2014 Scikit-learn: Machine Learning in Python JMLR 2011