Rushil Anirudh

D93CCDC5-529F-4134-A5E8-909F0A40649D

Hi! I am a machine learning scientist with the Machine Intelligence Group at Lawrence Livermore National Laboratory (LLNL).

My CV (pdf, updated July 2022).

Recent Updates

(9/14) Single Model Uncertainty Estimation via Stochastic Data Centering
accepted for publication to NeurIPS 2022! 🎷 [paper]
TLDR: Simple, easy-to-implement, accurate epistemic uncertainty estimates via a trivial data centering operation

(9/2) OOD Detection using Neural Network Anchoring,
accepted for publication to ACML 2022! 🏖️ [paper] [code]
TLDR: Novel hetero-scedastic (varying per sample) temperature scaling strategy that improves OOD detection

(8/16) Improving Diversity with Adversarially Learned Transformations for Domain Generalization,
accepted for publication to WACV 2023! 🏖️ [paper] [code].
TLDR: Improves domain generalization performance by expanding the space of learnable augmentations.

(7/11) arxiv preprint: Revisiting Inlier and Outlier Specification for Improved Out-of-Distribution Detection
TLDR: Studies the relative importance of inliers vs outlier exposure for effective OOD detection