ICLR "provable guarantees" Papers
3 papers found
Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
Gautam Chandrasekaran, Adam Klivans, Lin Lin Lee et al.
ICLR 2025posterarXiv:2502.16021
1
citations
Provable unlearning in topic modeling and downstream tasks
Stanley Wei, Sadhika Malladi, Sanjeev Arora et al.
ICLR 2025posterarXiv:2411.12600
Provably Safeguarding a Classifier from OOD and Adversarial Samples
Nicolas Atienza, Johanne Cohen, Christophe Labreuche et al.
ICLR 2025posterarXiv:2501.10202