← Search

Zhou Zhai

2 accepted papers

2024

Learning Sampling Policy to Achieve Fewer Queries for Zeroth-Order Optimization

AISTATS 2024poster

Zeroth-order (ZO) methods, which use the finite difference of two function evaluations (also called ZO gradient) to approximate first-order gradient, have attracted much attention recently in machine learning because of their broad applications. The accuracy of the ZO gradient highly depends on how…

Cited by 0SourcePDFScholar
2023

Faster Fair Machine via Transferring Fairness Constraints to Virtual Samples

AAAI 2023technical

Fair classification is an emerging and important research topic in machine learning community. Existing methods usually formulate the fairness metrics as additional inequality constraints, and then embed them into the original objective. This makes fair classification problems unable to be effective…

Cited by 0SourcePDFScholar