Unsupervised Transfer Learning via Adversarial Contrastive Training

1 code implementation • 16 Aug 2024 • Chenguang Duan, Yuling Jiao, Huazhen Lin, Wensen Ma, Jerry Zhijian Yang

Learning a data representation for downstream supervised learning tasks under unlabeled scenario is both critical and challenging.

Data Augmentation Self-Supervised Learning +1

Characteristic Learning for Provable One Step Generation

1 code implementation • 9 May 2024 • Zhao Ding, Chenguang Duan, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang, Pingwen Zhang

We propose the characteristic generator, a novel one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models.

Semi-Supervised Deep Sobolev Regression: Estimation, Variable Selection and Beyond

no code implementations • 9 Jan 2024 • Zhao Ding, Chenguang Duan, Yuling Jiao, Jerry Zhijian Yang

We propose SDORE, a semi-supervised deep Sobolev regressor, for the nonparametric estimation of the underlying regression function and its gradient.

regression Variable Selection

Current density impedance imaging with PINNs

no code implementations • 24 Jun 2023 • Chenguang Duan, Yuling Jiao, Xiliang Lu, Jerry Zhijian Yang

In this paper, we introduce CDII-PINNs, a computationally efficient method for solving CDII using PINNs in the framework of Tikhonov regularization.