← Search

Wu S. Zihan

1 accepted papers

2026

Can local learning match self-supervised backpropagation?

ICML 2026poster

While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local self-supervised learning (local-SSL) have struggled to build functional representations in deep neural networks. To establish a link between global and …

Cited by 0SourceScholar