ENTROPY-REGULARIZED OPTIMAL TRANSPORT GENERATIVE MODELS

被引:0
|
作者
Liu, Dong [1 ]
Minh Thanh Vu [1 ]
Chatterjee, Saikat [1 ]
Rasmussen, Lars K. [1 ]
机构
[1] KTH Royal Inst Technol, Stockholm, Sweden
关键词
Optimal transport; generative models;
D O I
10.1109/icassp.2019.8682721
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions. Two generative models are proposed. One uses EOT cost directly in an one-shot optimization problem and the other uses EOT cost iteratively in an adversarial game. The proposed generative models show improved performance over contemporary models on scores of sample based test.
引用
收藏
页码:3532 / 3536
页数:5
相关论文
共 50 条
  • [41] Regularized Discrete Optimal Transport
    Ferradans, Sira
    Papadakis, Nicolas
    Peyre, Gabriel
    Aujol, Jean-Francois
    [J]. SIAM JOURNAL ON IMAGING SCIENCES, 2014, 7 (03): : 1853 - 1882
  • [42] Quadratically Regularized Optimal Transport
    Dirk A. Lorenz
    Paul Manns
    Christian Meyer
    [J]. Applied Mathematics & Optimization, 2021, 83 : 1919 - 1949
  • [43] Semidual Regularized Optimal Transport
    Cuturi, Marco
    Peyre, Gabriel
    [J]. SIAM REVIEW, 2018, 60 (04) : 941 - 965
  • [44] Quadratically Regularized Optimal Transport
    Lorenz, Dirk A.
    Manns, Paul
    Meyer, Christian
    [J]. APPLIED MATHEMATICS AND OPTIMIZATION, 2021, 83 (03): : 1919 - 1949
  • [45] Shaping Large Population Agent Behaviors Through Entropy-Regularized Mean-Field Games
    Guan, Yue
    Zhou, Mi
    Pakniyat, Ali
    Tsiotras, Panagiotis
    [J]. 2022 AMERICAN CONTROL CONFERENCE, ACC, 2022, : 4429 - 4435
  • [46] NON-COHERENT SENSOR FUSION VIA ENTROPY REGULARIZED OPTIMAL MASS TRANSPORT
    Elvander, Filip
    Haasler, Isabel
    Jakobsson, Andreas
    Karlsson, Johan
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 4415 - 4419
  • [47] Optimal Transport for Deep Generative Models: State of the Art and Research Challenges
    Huynh, Viet
    Phung, Dinh
    Zhao, He
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4450 - 4457
  • [48] Learning Nash Equilibria in Zero-Sum Stochastic Games via Entropy-Regularized Policy Approximation
    Guan, Yue
    Zhang, Qifan
    Tsiotras, Panagiotis
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 2462 - 2468
  • [49] On Consistent Entropy-Regularized k-Means Clustering With Feature Weight Learning: Algorithm and Statistical Analyses
    Chakraborty, Saptarshi
    Paul, Debolina
    Das, Swagatam
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (08) : 4779 - 4790
  • [50] Volume preserving image segmentation with entropy regularized optimal transport and its applications in deep learning
    Li, Haifeng
    Liu, Jun
    Cui, Li
    Huang, Haiyang
    Tai, Xue-Cheng
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2020, 71