The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Spurious Local Minima Provably Exist for Deep CNNs: Theory and Application
- Published
- Record updated
Summary
The authors prove that a general family of spurious local minima exists in the loss landscape of deep CNNs with strictly convex losses and ReLU activations, for arbitrary architectures. They build the minima by pairing a local minimum with a second parameter point of equal empirical risk, then design a deterministic optimizer that escapes local minima. On CIFAR-10, CIFAR-100 and ImageNet-1k, it beats SGD or Adam in accuracy by 0.27% on average across CNNs, ResNets, MLPs and transformers.