← Search

Muqi Han

2 accepted papers

2026

$\texttt{MetaDistill}$: Unlocking the Performance Ceiling for Pretrained Optimizers

ICML 2026poster

Meta Black-Box Optimization (MetaBBO) has emerged as a promising paradigm by employing meta learning to automatically optimize the configurations of low-level black-box optimizers. Despite its potential, the generalization of MetaBBO remains significantly constrained when facing unseen, complex obje…

Cited by 0SourceScholar
2025

Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation

NeurIPS 2025poster

Zero-shot optimization aims to achieve both generalization and performance gains on solving previously unseen black-box optimization problems over SOTA methods without task-specific tuning. Pre-trained optimization models (POMs) address this challenge by learning a general mapping from task features…

Cited by 0SourceScholar