Publications

Google Scholar Page for a list of my most recent preprints.

Optimal Transport Related

• M. Scetbon, M. Klein, G. Palla, MC Unbalanced Low-Rank Optimal Transport Solvers, NeurIPS 2023

• MC, M. Klein, P. Ablin, Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps, ICML 2023

• T. Uscidda, MC, The Monge Gap: A Regularizer to Learn All Transport Maps, ICML 2023

• J. Thornton, MC, Rethinking Initialization of the Sinkhorn Algorithm, AISTATS 2023

• C. Bunne, Y.-P. Hsieh, MC, A. Krause, Recovering Stochastic Dynamics via Gaussian Schrödinger Bridges, AISTATS 2023

• C. Bunne, A. Krause, MC, Supervised Training of Conditional Monge Maps, NeurIPS 2022

• M. Scetbon, MC, Low-Rank Optimal Transport: Approximation, Statistics and Debiasing, NeurIPS 2022

• M. Blondel, Q. Berthet, MC, R. Frostig, S. Hoyer, F. Llinares-López, F. Pedregosa, J.-P. Vert Efficient and Modular Implicit Differentiation, NeurIPS 2022

• M. Scetbon, G. Peyré, MC, Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs, ICML 2022

• A.-A. Pooladian, MC, J. Niles-Weed, Debiaser Beware: Pitfalls of Centering Regularized Transport Maps, ICML 2022

• T. Lin, N. Ho, MC, M. Jordan, On the Complexity of Approximating Multimarginal Optimal Transport, JMLR (23) 65

• Y. Tian, MC, D. Ha, Simultaneous Multiple-Prompt Guided Generation Using Differentiable Optimal Transport, ICCC 2022

• C. Bunne, L. Meng-Papaxanthos, A. Krause, MC, Proximal Optimal Transport Modeling of Population Dynamics, AISTATS 2022

• O. Sebbouh, MC, G. Peyré, Randomized Stochastic Gradient Descent Ascent, AISTATS 2022

• M. Scetbon, MC, G. Peyré, Low-Rank Sinkhorn Factorization, ICML 2021

• Tianyi Lin, Zeyu Zheng, Elynn Y. Chen, MC, Michael I. Jordan, On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification, AISTATS 2021

• M. Scetbon, L. Meunier, J. Atif, MC, Equitable and Optimal Transport with Multiple Agents, AISTATS 2021

• M. Heitz, N. Bonneel, D. Coeurjolly, MC, G. Peyré, Ground Metric Learning on Graphs, Journal of Mathematical Imaging and Vision, 1-19

• T. Lin, C. Fan, N. Ho, MC, M.I. Jordan, Projection Robust Wasserstein Distance and Riemannian Optimization, NeurIPS 2020

• M. Scetbon, MC, Linear Time Sinkhorn Divergences using Positive Features, NeurIPS 2020

• H. Janati, B. Muzellec, G. Peyré, MC, Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form, NeurIPS 2020 (oral)

• Q. Berthet, M. Blondel, O. Teboul, MC, J.-P. Vert, F. Bach, Learning with differentiable perturbed optimizers, NeurIPS 2020

• T. Lin, N. Ho, X. Chen, MC, M.I. Jordan, Fixed-Support Wasserstein Barycenters:Computational Hardness and Fast Algorithm, NeurIPS 2020

• H. Janati, T. Bazeille, B. Thirion, MC, A. Gramfort, Multi-subject MEG/EEG source imaging with sparse multi-task regression, Neuroimage, 2020

• B. Muzellec, J. Josse, C. Boyer, MC, Missing Data Imputation using Optimal Transport, ICML 2020

• H. Janati, MC, A. Gramfort, Debiased Sinkhorn Barycenters, ICML 2020

• MC, O. Teboul, J. Niles-Weed, J.-P. Vert, Supervised Quantile Normalization for Low Rank Matrix Factorization, ICML 2020

• F.P. Paty, MC, Regularized Optimal Transport is Ground Cost Adversarial, ICML 2020

• F.P. Paty, A. d'Aspremont, MC, Regularity as regularization: Smooth and strongly convex brenier potentials in optimal transport, AISTATS 2020 (Notable paper award)

• H. Janati, MC, A. Gramfort, Spatio-Temporal Alignments: Optimal transport through space and time, AISTATS 2020.

• J. Djolonga, M. Lucic, MC, O. Bachem, O. Bousquet, Sylvain Gelly Evaluating Generative Models Using Divergence Frontiers, AISTATS 2020.

• MC, O. Teboul, J.P. Vert, Differentiable Sorting using Optimal Transport, Neurips 2019.

• B. Muzellec, MC, Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections, Neurips 2019.

• T. Le, M. Yamada, K. Fukumizu, MC, Tree-Sliced Variants of Wasserstein Distances, Neurips 2019.

• F.P. Paty, MC, Subspace Robust Wasserstein Distances, ICML 2019.

• G. de Bie, G. Peyré, MC, Stochastic Deep Networks, ICML 2019.

• H. Janati, T. Bazeille, B. Thirion, MC, A. Gramfort, Group level MEG/EEG source imaging via optimal transport: minimum Wasserstein estimates, IPMI, 2019.

• G. Peyré, MC, Computational Optimal Transport, FnT in Machine Learning, 11(5-6), 2019.

• S.-I. Amari, R. Karakida, M. Oizumi, MC, Information Geometry for Regularized Optimal Transport and Barycenters of Patterns, Neural Computation, 2019.

• A. Genevay, L. Chizat, F. Bach, MC, G. Peyré, Sample Complexity of Sinkhorn Divergences, AISTATS 2019.

• H. Janati, MC, A. Gramfort, Wasserstein Regularization for Sparse Multi-task Regression, AISTATS 2019.

• J. Alaux, E. Grave, MC, A. Joulin Unsupervised Hyper-alignment for Multilingual Word Embeddings, ICLR 2019.

• MC, G. Peyré, Semidual Regularized Optimal Transport, SIAM Review, 2018

• T. Lacombe, MC, S. Oudot, Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport, NeurIPS 2018.

• B. Muzellec, MC, Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions, NeurIPS 2018.

• R. Flamary, MC, N. Courty, A. Rakotomamonjy, Wasserstein Discriminant Analysis, Machine Learning Journal, 2018.

• E. Cazelles, V. Seguy, J. Bigot, MC, N. Papadakis, Log-PCA versus Geodesic PCA of histograms in the Wasserstein space, to appear in SIAM J. on Scient. Comput., 2018

• M.A. Schmitz, M. Heitz, N. Bonneel, F.M. Ngolè Mboula, D. Coeurjolly, MC, G. Peyré, J.-L. Starck, Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning, SIAM J. Imaging Sci. (11-1), 2018

• A. Genevay, G. Peyré, MC, Learning Generative Models with Sinkhorn Divergences, AISTATS 2018.

• M. Carrière, MC, S. Oudot, Sliced Wasserstein Kernel for Persistence Diagrams, ICML 2017.

• A. Ramdas, N. García Trillos, MC, On Wasserstein Two-Sample Testing and Related Families of Nonparametric Tests, Entropy 19(2), 2017

• A. Genevay, MC, G. Peyré, F. Bach, Stochastic Optimization for Large-scale Optimal Transport, NIPS 2016.

• G. Montavon, K.-R. Müller, MC, Wasserstein Training of Restricted Boltzmann Machines, NIPS 2016.

• G. Peyré, MC, J. Solomon, Gromov-Wasserstein Averaging of Kernel and Distance Matrices, ICML 2016.

• N. Bonneel, G. Peyré, MC, Wasserstein Barycentric Coordinates: Histogram Regression Using Optimal Transport, SIGGRAPH 2016.

• A. Rolet, MC, G. Peyré, Fast Dictionary Learning with a Smoothed Wasserstein Loss, AISTATS 2016.

• MC, G. Peyré, A Smoothed Dual Formulation for Variational Wasserstein Problems, SIAM J. Imaging Sci. (9-1), 2016.

• V. Seguy, MC, Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric, NIPS 2015.

• J. Solomon, F. de Goes, G. Peyré, MC, A. Butscher, A. Nguyen, T. Du, L. Guibas, Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains, SIGGRAPH 2015.

• J.D. Benamou, G. Carlier, MC, L. Nenna, G. Peyré, Iterative Bregman Projections for Regularized Transportation Problems, SIAM J. on Scient. Comput.(37-2), 2015.

• A. Gramfort, G. Peyré, MC, Fast Optimal Transport Averaging of Neuroimaging Data, IPMI 2015.

• MC, A. Doucet, Fast Computation of Wasserstein Barycenters, ICML 2014.

• MC, D. Avis, Ground Metric Learning, JMLR, 2014.

• MC, Sinkhorn Distances: Lightspeed Computation of Optimal Transport, NIPS 2013.

• MC, Permanents, Transportation Polytopes and Positive Definite Kernels on Histograms, IJCAI 2007. Note: the proof of Prop.3 in that paper is wrong. See this paper for a correct result.

Time Series

• MC, M. Blondel, Soft-DTW: A Differentiable Loss Function for Time Series, ICML 2017.

• MC, A. d'Aspremont, Mean-Reverting Portfolios: Tradeoffs Between Sparsity and Volatility, Financial Signal Processing and Machine Learning, Wiley, 2016.

• MC, A. d'Aspremont, Mean Reversion with a Variance Threshold, ICML 2013.

• MC, Fast Global Alignment Kernels, ICML 2011.

• MC , J.-P. Vert, O. Birkenes, T. Matsui, A Kernel for Time Series based on Global Alignments, ICASSP 2007.

Kernels / Metrics for Structured Data

• T. Le, MC, Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations, ICML 2015.

• T. Le, MC, Adaptive Euclidean Maps for Histograms: Generalized Aitchison Embeddings, Machine Learning Journal, 2014.

• T. Le, MC, Generalized Aitchison Embeddings for Histograms, ACML 2013.

• K. Shin, MC, T. Kuboyama, Mapping Kernels for Trees, ICML 2011.

• MC , J.-P. Vert, A. d'Aspremont, White Functionals for Anomaly Detection in Dynamical Systems, NIPS 2009.

• MC, K. Fukumizu, Kernels on Structured Objects Through Nested Histograms, NIPS 2006.

• MC, K. Fukumizu, J.-P. Vert, Semigroup Kernels on Measures , JMLR vol.6 (Jul):1169–1198, 2005.

• MC, J.-P. Vert, Semigroup Kernels on Finite Sets, NIPS 2004.

• MC, J.-P. Vert, The Context-Tree Kernel for Strings, Neural Networks, Volume 18, Issue 8, 2005.

• MC, J.-P. Vert, A Mutual Information Kernel for Sequences, IJCNN 2004.

Working Papers

• MC, Positivity and Transportation, arXiv:1209.2655, 2012.

• MC, A. Doucet, Autoregressive Kernels for Time Series, arXiv:1101.0673, 2011.

• MC, Positive Definite Kernels in Machine Learning, a survey and teaching document (draft), 2010.

• MC, Kernels for Measures Defined on the Gram Matrix of their Support, arXiv:0909.0991v1, 2009.