← Search

Le Quang Dung

2 accepted papers

2025

On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts

NeurIPS 2025poster

The softmax-contaminated mixture of experts (MoE) model is deployed when a large-scale pre-trained model, which plays the role of a fixed expert, is fine-tuned for learning downstream tasks by including a new contamination part, or prompt, functioning as a new, trainable expert. Despite its populari…

Cited by 0SourceScholar
2025

Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts

AISTATS 2025poster

We conduct the convergence analysis of parameter estimation in the contaminated mixture of experts. This model is motivated from the prompt learning problem where ones utilize prompts, which can be formulated as experts, to fine-tune a large-scale pre-trained model for learning downstream tasks. The…

Cited by 0SourceScholar