My research interests lie at the interface of statistics and machine learning with the goal of developing effective machine learning algorithms with theoretical guarantees. Currently, I am working on causal inference, disentanglement, and generative models (e.g., GANs).
Weakly Supervised Disentangled Generative Causal Representation Learning X. Shen, F. Liu, H. Dong, Q. Lian, Z. Chen, T. Zhang
Journal of Machine Learning Research, vol. 23, pp. 1-55, 2022 | paper | code | slides
Surprise Sampling: Improving and Extending the Local Case-Control Sampling X. Shen, K. Chen, W. Yu
Electron. J. Statist., vol. 15, pp. 2454-2482, 2021 | paper
In vivo single-cell lineage tracing in zebrafish using high-resolution infrared laser-mediated gene induction microscopy
S. He, Y. Tian, S. Feng, Y. Wu, X. Shen, K. Chen, Y. He, et al.
Elife, vol. 9, e52024, 2020 | paper
Conference Publications:
Reframed GES with a Neural Conditional Dependence Measure X. Shen, S. Zhu, J. Zhang, S. Hu, Z. Chen
UAI, 2022 | paper | code
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation
S. Diao*, X. Shen*, K. S. Shum, Y. Song, T. Zhang
Findings of ACL, 2021 (*equal contribution) | paper | code
CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models
M. Yang, F. Liu, Z. Chen, X. Shen, J. Hao, J. Wang
CVPR, 2021 | paper | code
Preprints:
Bidirectional Generative Modeling Using Adversarial Gradient Estimation X. Shen, T. Zhang, K. Chen
paper | code
Asymptotic Statistical Analysis of f-divergence GAN X. Shen, K. Chen, T. Zhang
Available upon request
To ArXiv or not to ArXiv: A Study Quantifying Pros and Cons of Posting Preprints
C. Rastogi, I. Stelmakh, X. Shen, M. Meila, F. Echenique, S. Chawla, N. B Shah
paper