CATCH Principal Investigators and researchers have had 7 full papers accepted to NeurIPS 2023, the premier venue for machine learning research, internationally. Congrats to all involved!

Our researchers are grateful to the support of ARO, DSTG/DISR, and the CATCH program managers.

The papers’ authors are keen for feedback from the community. Interested researchers are most welcome to attend the corresponding talks/visit posters at NeurIPS in New Orleans in December 2023, or reach out by email.

Neurips 2023 CATCH papers

  • Mechanism design for collaborative normal mean estimation. Yiding Chen, Xiaojin Zhu, and Kirthevasan Kandasamy. Spotlight.

  • Grounding Neural Inference with Satisfiability Modulo Theories. Matt Fredrikson, Kaiji Lu, Somesh Jha, Saranya Vijayakumar, Vijay Ganesh, Zifan Wang. Spotlight.

  • RS-Del: Edit distance robustness certificates for sequence classifiers via randomized deletion. Zhuoqun Huang, Neil G. Marchant, Keane Lucas, Lujo Bauer, Olga Ohrimenko, and Benjamin I. P. Rubinstein.

  • Scaling in Depth: Unlocking Robustness Certification on ImageNet. Kai Hu, Andy Zou, Zifan Wang, Klas Leino, Matt Fredrikson.

  • Dream the impossible: Outlier imagination with diffusion models. Xuefeng Du, Yiyou Sun, Xiaojin Zhu, and Yixuan Li.

  • Doubly Robust Peer-To-Peer Learning Protocol Nicholas Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser, Congyu Fang, Somesh Jha, Nicolas Papernot, Xiao Wang.

  • Agnostic Multi-group Active Learning Nicholas Rittler and Kamalika Chaudhuri.