Document detail
ID
oai:arXiv.org:2406.02317
Topic
Computer Science - Machine Learnin... Computer Science - Artificial Inte... Statistics - Machine LearningAuthor
Nguyen, Bao Nguyen, Binh Nguyen, Hieu Trung Nguyen, Viet AnhCategory
Computer Science
Year
2024
listing date
6/12/2024
Keywords
neural network generative learningAbstract
Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates.
We introduce a novel neural entropic optimal transport method designed to effectively learn generative models of conditional distributions, particularly in scenarios characterized by limited sample sizes.
Our method relies on the minimax training of two neural networks: a generative network parametrizing the inverse cumulative distribution functions of the conditional distributions and another network parametrizing the conditional Kantorovich potential.
To prevent overfitting, we regularize the objective function by penalizing the Lipschitz constant of the network output.
Our experiments on real-world datasets show the effectiveness of our algorithm compared to state-of-the-art conditional distribution learning techniques.
Our implementation can be found at https://github.com/nguyenngocbaocmt02/GENTLE.
;Comment: 15 pages, 8 figures
Nguyen, Bao,Nguyen, Binh,Nguyen, Hieu Trung,Nguyen, Viet Anh, 2024, Generative Conditional Distributions by Neural (Entropic) Optimal Transport
UniZero: Generalized and Efficient Planning with Scalable Latent World Models
unizero latent learning
Reconstruction of the Corticospinal Tract in Patients with Motor-Eloquent High-Grade Gliomas Using Multilevel Fiber Tractography Combined with Functional Motor Cortex Mapping
mapping motor-eloquent threshold anisotropy spherical gliomas patients corticospinal tract tractography
