Selected Publications on Theory (Hierarchical and Mixture Models, Bayesian Nonparametrics, Optimal Transport, Deep Learning, (Approximate) Bayesian Inference, (Non)-Convex Optimization, etc.)
*= equal contribution
**= alphabetical order
†= co-last author
- Instability, computational efficiency, and statistical accuracy . Journal of Machine Learning Research (JMLR), 2025.
Nhat Ho*, Raaz Dwivedi*, Koulik Khamaru*, Martin J. Wainwright, Michael I. Jordan, Bin Yu.
- On DeepSeekMoE: Statistical benefits of shared experts and normalized sigmoid gating . Under review.
Huy Nguyen, Thong Doan, Quang Pham, Nghi Bui, Nhat Ho†, Alessandro Rinaldo†.
- Sigmoid self-attention is better than softmax self-attention: A mixture-of-experts perspective . Under review.
Fanqi Yan*, Huy Nguyen*, Pedram Akbarian, Nhat Ho†, Alessandro Rinaldo†.
- Adaptive prompt: Unlocking the power of visual prompt tuning. Under review.
Minh Le*, Anh Nguyen*, Huy Nguyen, Chau Nguyen, Nhat Ho.
- RepLoRA: Reparameterizing low-rank adaptation via the perspective of mixture of experts. Proceedings of the ICML, 2025.
Tuan Truong*, Chau Nguyen*, Huy Nguyen*, Minh Le, Trung Le, Nhat Ho.
- On zero-initialized attention: Optimal prompt and gating factor estimation. Proceedings of the ICML, 2025.
Nghiem Diep*, Huy Nguyen*, Chau Nguyen*, Minh Le, Duy Nguyen, Daniel Sonntag, Mathias Niepert, Nhat Ho.
- On expert estimation in hierarchical mixture of experts: Beyond softmax gating functions . Under review.
Huy Nguyen*, Xing Han*, Carl Harris, Suchi Saria, Nhat Ho.
- Quadratic gating functions in mixture of experts: A statistical insight . Under review.
Pedram Akbarian*, Huy Nguyen*, Xing Han*, Nhat Ho.
- Revisiting prefix-tuning: Statistical benefits of reparameterization among prompts . ICLR, 2025.
Minh Le*, Chau Nguyen*, Huy Nguyen*, Quyen Tran, Trung Le, Nhat Ho.
- Statistical advantages of perturbing cosine router in sparse mixture of experts . ICLR, 2025.
Huy Nguyen, Pedram Akbarian*, Trang Pham*, Trang Nguyen*, Shujian Zhang Nhat Ho.
