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
- Is temperature sample efficient for softmax Gaussian mixture of experts? . Proceedings of the ICML, 2024.
Huy Nguyen, Pedram Akbarian, Nhat Ho.
- Bayesian nonparametrics meets data-driven robust optimization . Advances in NeurIPS, 2024.
Nicola Bariletto, Nhat Ho.
- Sigmoid gating is more sample efficient than softmax gating in mixture of experts . Advances in NeurIPS, 2024.
Huy Nguyen, Nhat Ho†, Alessandro Rinaldo†.
- On barycenter computation: Semi-unbalanced optimal transport-based method on Gaussians . Under review.
Hai Nguyen*, Dung Le*, Phi Nguyen, Tung Pham, Nhat Ho.
- Borrowing strength in distributionally robust optimization via hierarchical Dirichlet processes . Under review.
Nicola Bariletto, Khai Nguyen, Nhat Ho.
- On least square estimation in softmax gating mixture of experts . Proceedings of the ICML, 2024.
Huy Nguyen, Nhat Ho†, Alessandro Rinaldo†.
- Statistical perspective of top-K sparse softmax gating mixture of experts . ICLR, 2024.
Huy Nguyen, Pedram Akbarian, Fanqi Yan, Nhat Ho.
- Towards convergence rates for parameter estimation in Gaussian-gated mixture of experts . AISTATS, 2024.
Huy Nguyen, Tin Nguyen, Khai Nguyen, Nhat Ho.
- Neural collapse for cross-entropy class-imbalanced learning with unconstrained ReLU feature model . Proceedings of the ICML, 2024.
Hien Dang, Tho Tran, Tan Nguyen†, Nhat Ho†.
- A general theory for softmax gating multinomial logistic mixture of experts . Proceedings of the ICML, 2024.
Huy Nguyen, Pedram Akbarian, Tin Nguyen, Nhat Ho.
- Beyond vanilla variational autoencoders: Detecting posterior collapse in conditional and hierarchical variational autoencoders . ICLR, 2024.
Hien Dang, Tho Tran, Tan Nguyen†, Nhat Ho†.
- On integral theorems and their statistical properties . Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2024.
Nhat Ho**, Stephen G. Walker**.
- On the computational and statistical complexity of over-parameterized matrix sensing . Journal of Machine Learning Research (JMLR), 2024.
Jiacheng Zhuo, Jeongyeol Kwon, Nhat Ho, Constantine Caramanis.
- Improving computational complexity in statistical models with second-order information . Proceedings of the ICML, 2024.
Tongzheng Ren, Jiacheng Zhuo, Sujay Sanghavi, Nhat Ho.
