7 papers
Deconfounding via Profiled Transfer Learning
Ziyuan Chen, Yifan Jiang, Jingyuan Liu +1
Unmeasured confounders are a major source of bias in regression-based effect estimation and causal inference. In this paper, we propose a new profiled transfer learning framework,…
Dynamic Matrix Recovery
Ziyuan Chen, Ying Yang, Fang Yao
Matrix recovery from sparse observations is an extensively studied topic emerging in various applications, such as recommendation system and signal processing, which includes the m…
Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models
Ziyuan Chen, Yujin Jeong, Tobias Braun +1
As text-to-image diffusion models become increasingly deployed in real-world applications, concerns about backdoor attacks have gained significant attention. Prior work on text-bas…
Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping
Pu Yang, Yunzhen Feng, Ziyuan Chen +2
Modern foundation models often undergo iterative ``bootstrapping'' in their post-training phase: a model generates synthetic data, an external verifier filters out low-quality samp…
Deep Semiparametric Partial Differential Equation Models
Ziyuan Chen, Shunxing Yan, Fang Yao
In many scientific fields, the generation and evolution of data are governed by partial differential equations (PDEs) which are typically informed by established physical laws at t…
Semiparametric M-estimation with overparameterized neural networks
Shunxing Yan, Ziyuan Chen, Fang Yao
We focus on semiparametric regression that has played a central role in statistics, and exploit the powerful learning ability of deep neural networks (DNNs) while enabling statisti…