Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks

Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li
2/12/2026
Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{li2026feature,
  title  = {Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks},
  author = {Binghui Li and Zhixuan Pan and Kaifeng Lyu and Jian Li},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:d21b8651578de4e664730141675489e1460369ab},
  journal = {ICLR 2025 2025}
}

Discussion