Xianhua Liu

OVLR: Efficient, Scalable, and Robust Training via Output-Level Variance-Reduced Likelihood Ratio

Gradient-based optimization is fundamental to deep learning, yet standard backpropagation (BP) is inherently limited by the requirement of differentiability, rendering it brittle when encountering piecewise-constant objectives with vanishing gradients (e.g., hard 0-1 loss) or black-box feedback. Whi…