Timezone: »
Estimating optimal transport (OT) maps (a.k.a. Monge maps) between two measures P and Q is a problem fraught with computational and statistical challenges. A promising approach lies in using the dual potential functions obtained when solving an entropy-regularized OT problem between samples Pn and Qn, which can be used to recover an approximately optimal map. The negentropy penalization in that scheme introduces, however, an estimation bias that grows with the regularization strength. A well-known remedy to debias such estimates, which has gained wide popularity among practitioners of regularized OT, is to center them, by subtracting auxiliary problems involving Pn and itself, as well as Qn and itself. We do prove that, under favorable conditions on P and Q, debiasing can yield better approximations to the Monge map. However, and perhaps surprisingly, we present a few cases in which debiasing is provably detrimental in a statistical sense, notably when the regularization strength is large or the number of samples is small. These claims are validated experimentally on synthetic and real datasets, and should reopen the debate on whether debiasing is needed when using entropic OT.
Author Information
Aram-Alexandre Pooladian (New York University)
Marco Cuturi (Apple and ENSAE/CREST)

Marco is a researcher in machine learning at Apple, working since Jan. 2022 in the Machine Learning Research team led by Samy Bengio. Marco has also been affiliated with the ENSAE / IP Paris school since 2016, working there part-time from 2018. Marco also worked at Google Brain (2018~2022), Kyoto University (2010~2016), Princeton University (2009~2010), the financial industry (2007~2008) and the Institute of Statistical Mathematics (Tokyo, 2006~2007). Marco received his Ph.D. in 2005 from Ecole des Mines de Paris. Marco's research interests cover differentiable optimization, time series, optimal transport theory and its application to ML.
Jonathan Niles-Weed (NYU)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Debiaser Beware: Pitfalls of Centering Regularized Transport Maps »
Thu. Jul 21st 08:35 -- 08:40 PM Room Room 318 - 320
More from the Same Authors
-
2023 Poster: Minimax estimation of discontinuous optimal transport maps: The semi-discrete case »
Aram-Alexandre Pooladian · Vincent Divol · Jonathan Niles-Weed -
2023 Poster: Perturbation Analysis of Neural Collapse »
Tom Tirer · Haoxiang Huang · Jonathan Niles-Weed -
2023 Workshop: Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators »
Felix Petersen · Marco Cuturi · Mathias Niepert · Hilde Kuehne · Michael Kagan · Willie Neiswanger · Stefano Ermon -
2022 Poster: Deep Probability Estimation »
Sheng Liu · Aakash Kaku · Weicheng Zhu · Matan Leibovich · Sreyas Mohan · Boyang Yu · Haoxiang Huang · Laure Zanna · Narges Razavian · Jonathan Niles-Weed · Carlos Fernandez-Granda -
2022 Spotlight: Deep Probability Estimation »
Sheng Liu · Aakash Kaku · Weicheng Zhu · Matan Leibovich · Sreyas Mohan · Boyang Yu · Haoxiang Huang · Laure Zanna · Narges Razavian · Jonathan Niles-Weed · Carlos Fernandez-Granda -
2020 Poster: Supervised Quantile Normalization for Low Rank Matrix Factorization »
Marco Cuturi · Olivier Teboul · Jonathan Niles-Weed · Jean-Philippe Vert