3 papers
math.ST2026
Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity
Fanqi Yan, Dung Le, Trang Pham +2
Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioni…
stat.ML2025
Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
Huy Nguyen, Pedram Akbarian, Trang Pham +3
The cosine router in Mixture of Experts (MoE) has recently emerged as an attractive alternative to the conventional linear router. Indeed, the cosine router demonstrates favorable…
cs.LG2025
Mixture of Experts Meets Prompt-Based Continual Learning
Minh Le, An Nguyen, Huy Nguyen +4
Exploiting the power of pre-trained models, prompt-based approaches stand out compared to other continual learning solutions in effectively preventing catastrophic forgetting, even…