Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality

Sungyoon Kim, Aaron Mishkin, Mert Pilanci
2/12/2026

No official code found. Best implementation: pilancilab/Loss-landscape-convex-duality (1 star, last commit 2025-02-27).

Semantic Scholar

Code Implementations(1)

pilancilab/Loss-landscape-convex-dualityCommunity68%

Code for Exploring the loss landscape of regularized neural networks via convex duality

10Jupyter NotebookFeb 27, 20251 years ago

Cite this paper

@article{kim2026exploring,
  title  = {Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality},
  author = {Sungyoon Kim and Aaron Mishkin and Mert Pilanci},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:bddbf21a660c0eaeeaf89f01267be40805ae3f28},
  journal = {ICLR 2025 2025}
}

Discussion