2 citations · 2 across the 11 of their papers we have counts for
10 papers · 1 filter
CARE: Turning LLMs Into Causal Reasoning Expert
Juncheng Dong, Yiling Liu, Ahmed Aloui +2
Large language models (LLMs) have recently demonstrated impressive capabilities across a range of reasoning and generation tasks. However, research studies have shown that LLMs lac…
Conditional Average Treatment Effect Estimation Under Hidden Confounders
Ahmed Aloui, Juncheng Dong, Ali Hasan +1
One of the major challenges in estimating conditional potential outcomes and conditional average treatment effects (CATE) is the presence of hidden confounders. Since testing for h…
Teleportation With Null Space Gradient Projection for Optimization Acceleration
Zihao Wu, Juncheng Dong, Ahmed Aloui +1
Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach,…
Score-Based Metropolis-Hastings Algorithms
Ahmed Aloui, Ali Hasan, Juncheng Dong +2
In this paper, we introduce a new approach for integrating score-based models with the Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in accura…
Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks
Shyam Venkatasubramanian, Ahmed Aloui, Vahid Tarokh
Advancing loss function design is pivotal for optimizing neural network training and performance. This work introduces Random Linear Projections (RLP) loss, a novel approach that e…
CATE Estimation With Potential Outcome Imputation From Local Regression
Ahmed Aloui, Juncheng Dong, Cat P. Le +1
One of the most significant challenges in Conditional Average Treatment Effect (CATE) estimation is the statistical discrepancy between distinct treatment groups. To address this i…
Causal Mediation Analysis with Multi-dimensional and Indirectly Observed Mediators
Ziyang Jiang, Yiling Liu, Michael H. Klein +5
Causal mediation analysis (CMA) is a powerful method to dissect the total effect of a treatment into direct and mediated effects within the potential outcome framework. This is imp…
Mode-Aware Continual Learning for Conditional Generative Adversarial Networks
Cat P. Le, Juncheng Dong, Ahmed Aloui +1
The main challenge in continual learning for generative models is to effectively learn new target modes with limited samples while preserving previously learned ones. To this end,…
Domain Adaptation via Rebalanced Sub-domain Alignment
Yiling Liu, Juncheng Dong, Ziyang Jiang +5
Unsupervised domain adaptation (UDA) is a technique used to transfer knowledge from a labeled source domain to a different but related unlabeled target domain. While many UDA metho…
Transfer Learning for Individual Treatment Effect Estimation
Ahmed Aloui, Juncheng Dong, Cat P. Le +1
This work considers the problem of transferring causal knowledge between tasks for Individual Treatment Effect (ITE) estimation. To this end, we theoretically assess the feasibilit…