| Certified adversarial robustness via randomized smoothing JM Cohen, E Rosenfeld, JZ Kolter Proceedings of the 36th International Conference on Machine Learning, 2019 | 2308 | 2019 |
| The Risks of Invariant Risk Minimization E Rosenfeld, P Ravikumar, A Risteski International Conference on Learning Representations, 2020 | 336 | 2020 |
| Certified robustness to label-flipping attacks via randomized smoothing E Rosenfeld, E Winston, P Ravikumar, JZ Kolter arXiv preprint arXiv:2002.03018, 2020 | 184 | 2020 |
| Domain-adjusted regression or: Erm may already learn features sufficient for out-of-distribution generalization E Rosenfeld, P Ravikumar, A Risteski arXiv preprint arXiv:2202.06856, 2022 | 87 | 2022 |
| Learning linear causal representations from interventions under general nonlinear mixing S Buchholz, G Rajendran, E Rosenfeld, B Aragam, B Schölkopf, ... Advances in Neural Information Processing Systems 36, 2024 | 54 | 2024 |
| Iterative feature matching: Toward provable domain generalization with logarithmic environments Y Chen, E Rosenfeld, M Sellke, T Ma, A Risteski Advances in Neural Information Processing Systems 35, 1725-1736, 2022 | 38 | 2022 |
| An online learning approach to interpolation and extrapolation in domain generalization E Rosenfeld, P Ravikumar, A Risteski International Conference on Artificial Intelligence and Statistics, 2021 | 34 | 2021 |
| Analyzing and improving the optimization landscape of noise-contrastive estimation B Liu, E Rosenfeld, P Ravikumar, A Risteski arXiv preprint arXiv:2110.11271, 2021 | 22 | 2021 |
| Certified adversarial robustness via randomized smoothing. 2019 J Cohen, E Rosenfeld, Z Kolter URL https://github. com/locuslab/smoothing, 1902 | 15* | 1902 |
| Identifying representations for intervention extrapolation S Saengkyongam, E Rosenfeld, P Ravikumar, N Pfister, J Peters arXiv preprint arXiv:2310.04295, 2023 | 12 | 2023 |
| Outliers with opposing signals have an outsized effect on neural network optimization E Rosenfeld, A Risteski arXiv preprint arXiv:2311.04163, 2023 | 9 | 2023 |
| Ape: Aligning pretrained encoders to quickly learn aligned multimodal representations E Rosenfeld, P Nakkiran, H Pouransari, O Tuzel, F Faghri arXiv preprint arXiv:2210.03927, 2022 | 6 | 2022 |
| One-shot strategic classification under unknown costs E Rosenfeld, N Rosenfeld arXiv preprint arXiv:2311.02761, 2023 | 5 | 2023 |
| Deep attentive variational inference I Apostolopoulou, I Char, E Rosenfeld, A Dubrawski International Conference on Learning Representations, 2021 | 5 | 2021 |
| Method and system to classify sensor data with improved training robustness EK Rosenfeld, EM Winston, F Schmidt, JZ Kolter US Patent App. 17/025,076, 2021 | 4 | 2021 |
| Human-Usable Password Schemas: Beyond Information-Theoretic Security E Rosenfeld, S Vempala, M Blum CMU Senior Honors Thesis, 2016 | 2 | 2016 |
| (Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy E Rosenfeld, S Garg Advances in Neural Information Processing Systems 36, 28761-28784, 2023 | | 2023 |
| Understanding, Formally Characterizing, and Robustly Handling Real-World Distribution Shift E Rosenfeld | | 2023 |
| Self-Reflective Variational Autoencoder I Apostolopoulou, E Rosenfeld, A Dubrawski arXiv preprint arXiv:2007.05166, 2020 | | 2020 |
| Loss in the Crowd: Hidden Breakthroughs in Language Model Training S Kangaslahti, E Rosenfeld, N Saphra ICML 2024 Workshop on Mechanistic Interpretability, 0 | | |
Pradeep RavikumarProfessor, School of Computer Science, Carnegie Mellon UniversityVerified email at cs.cmu.edu