Publications

Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately, Fereshte Khani, Percy Liang, ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2021 [code][blog post]

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness, Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang, International Conference on Learning Representations (ICLR) 2021

Feature Noise Induces Loss Discrepancy Across Groups, Fereshte Khani, Percy Liang, International Conference in Machine Learning (ICML), 2020 [slides][code][video][blog post]

Maximum Weighted Loss Discrepancy, Fereshte Khani, Aditi Raghunathan, Percy Liang. Safe Machine Learning workshop at the International Conference on Learning Representation (ICLR), 2019. [slides][poster][code]

Planning, Inference, and Pragmatics in Sequential Language Games, Fereshte Khani, Noah D. Goodman, Percy Liang. Transactions of the Association for Computational Linguistics (TACL), 2018. [slides][code][dataset]

Unanimous prediction for 100% precision with application to learning semantic mappings, Fereshte Khani, Martin Rinard, Percy Liang. Association for Computational Linguistics (ACL), 2016. [poster][code]

Learning precise partial semantic mappings via linear algebra, Fereshte Khani. Master thesis, Massachusetts Institute of Technology, 2016.

 An algorithm for discovering clusters of different densities or shapes in noisy data sets, Fereshte Khani, Mohammad Javad Hosseini, Ahmad Ali Abin, Hamid Beigy. ACM Symposium on Applied Computing (ACM-SAC), 2013.