2 papers
cs.LG2026
Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data
Sudeepta Mondal, Xinyi Mary Xie, Ruxiao Duan +2
Existing out-of-distribution (OOD) detectors are often tuned by a separate dataset deemed OOD with respect to the training distribution of a neural network (NN). OOD detectors proc…
cs.LG2025
An Information-Theoretic Framework for Feature Construction in Out-of-Distribution Detection
Sudeepta Mondal, Zhuolin Jiang, Xinyi +3
We present a theory for the construction of out-of-distribution (OOD) detection features for neural networks. We introduce random features for OOD through a novel information-theor…