William de Vazelhes

Dual Variance Reduction with Momentum for Imbalanced Black-Box Discrete Prompt Learning

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

Query Efficient Black-Box Adversarial Attack with Automatic Region Selection

Optimization over Sparse Restricted Convex Sets via Two Steps Projection