← Search

Ruoran Xu

2 accepted papers

2026

Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization

ICML 2026poster

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components like ReLU activations and quantization operators. In such non-smooth regimes, adaptive optimizers such as Adam suffer from g…

Cited by 0SourceScholar