Saurabh Garg, PhD Student
https://saurabhgarg1996.github.io/
Hello! My name is Saurabh Garg and I am a second-year Ph.D. student at Machine Learning Department at CMU where I am advised by Prof. Zachary Lipton and Prof. Siva Balakrishnan. I am broadly interested in building robust and interpretable machine learning systems. Machine learning algorithms are typically developed and evaluated under simplistic assumptions that are often violated in practice. I am interested in understanding the behavior of machine learning models in real-world scenarios and building provable methods to make progress towards relaxing simplifying assumptions in order to make robust and trustworthy models.
Research Interests: Robustness, Distribution Shift, NLP
Publications
Downstream Datasets Make Surprisingly Good Pretraining Corpora
Kundan Krishna, Saurabh Garg, Jeffrey Bigham, Zachary Lipton
ACL 2023, 2023Disentangling the Mechanisms Behind Implicit Regularization in SGD
Zachary Novack, Simran Kaur, Tanya Marwah, Saurabh Garg, Zachary Lipton
International Conference on Learning Representations (ICLR), 2023Deconstructing distributions: A pointwise framework of learning
Gal Kaplun, Nkhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran
International Conference on Learning Representations (ICLR), 2023Chils: Zero-shot image classification with hierarchical label sets
Zachary Novack, Julian McAuley, Zachary Lipton, Saurabh Garg
arXiv preprint arXiv:2302.02551, 2023RLSbench: Domain Adaptation Under Relaxed Label Shift
Saurabh Garg, Nick Erickson, James Sharpnack, Alex Smola, Sivaraman Balakrishnan, Zachary Lipton
arXiv preprint arXiv:2302.03020, 2023Unsupervised Learning under Latent Label Shift
Manley Roberts*, Pranav Mani*, Saurabh Garg, Zachary Lipton
Advances in Neural Information Processing Systems (NeurIPS), 2022Domain Adaptation under Open Set Label Shift
Saurabh Garg, Sivaraman Balakrishnan, Zachary Lipton
Advances in Neural Information Processing Systems (NeurIPS), 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Saurabh Garg, Sivaraman Balakrishnan, Zachary Lipton, Hanie Sedghi, Behnam Neyshabur
International Conference on Learning Representations (ICLR), 2022Mixture Proportion Estimation and PU Learning: A Modern Approach
Saurabh Garg, Yifan Wu, Alex Smola, Sivaraman Balakrishnan, Zachary Lipton
Advances in Neural Information Processing Systems (NeurIPS), 2021RATT: Leveraging Unlabeled Data to Guarantee Generalization
Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter, Zachary Lipton
International Conference on Machine Learning (ICML), 2021On Proximal Policy Optimization’s Heavy-Tailed Gradients
Saurabh Garg, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Zachary Lipton, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Pradeep Ravikumar
International Conference on Machine Learning (ICML), 2021A Unified View of Label Shift Estimation
Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan, Zachary Lipton
Advances in Neural Information Processing Systems (NeurIPS), 2020