2 papers
cs.LG2026
Targeted Regularization for Causal Effect Estimation with Exponential Dispersion Family Outcomes
Jiahong Li, Zeqin Yang, Jixing Xu +4
Neural Networks (NNs) for causal effect estimation have shown strong empirical performance, yet endowing them with desirable semiparametric properties -- doubly robustness and fast…
math.OC2025
Accelerated Gradient Methods with Gradient Restart: Global Linear Convergence
Chenglong Bao, Liang Chen, Jiahong Li +1
Gradient restarting has been shown to improve the numerical performance of accelerated gradient methods. This paper provides a mathematical analysis to understand these advantages.…