Follow
Saurabh Garg
Saurabh Garg
Mistral AI | Past: CMU ML PhD
Verified email at andrew.cmu.edu - Homepage
Title
Cited by
Cited by
Year
A Unified View of Label Shift Estimation
S Garg, Y Wu, S Balakrishnan, ZC Lipton
Advances in Neural Information Processing Systems (NeurIPS) 2020, 2020
1702020
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
S Garg, S Balakrishnan, ZC Lipton, B Neyshabur, H Sedghi
International Conference on Machine Learning (ICLR), 2022, 2022
1462022
Chils: Zero-shot image classification with hierarchical label sets
Z Novack, J McAuley, ZC Lipton, S Garg
International Conference of Machine Learning (ICML) 2023, 2023
782023
Mixture Proportion Estimation and PU Learning:A Modern Approach
S Garg, Y Wu, A Smola, S Balakrishnan, ZC Lipton
Advances in Neural Information Processing (NeurIPS) 2021, Spotlight, 2021
672021
Neural Architecture for Question Answering Using a Knowledge Graph and Web Corpus
U Sawant, S Garg, S Chakrabarti, G Ramakrishnan
Information Retrieval Journal, 2019, 2018
532018
Datacomp-lm: In search of the next generation of training sets for language models
J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, S Gadre, H Bansal, E Guha, ...
arXiv preprint arXiv:2406.11794, 2024
47*2024
Code-switched language models using dual rnns and same-source pretraining
S Garg, T Parekh, P Jyothi
Empirical Methods in Natural Language Processing (EMNLP), 2018, 2018
452018
Domain adaptation under open set label shift
S Garg, S Balakrishnan, ZC Lipton
Advances in Neural Information Processing (NeurIPS) 2022, 2022
392022
Characterizing Datapoints via Second-Split Forgetting
P Maini, S Garg, ZC Lipton, JZ Kolter
Advances in Neural Information Processing (NeurIPS) 2022, 2022
372022
RLSbench: Domain Adaptation Under Relaxed Label Shift
S Garg, N Erickson, J Sharpnack, A Smola, S Balakrishnan, ZC Lipton
International Conference of Machine Learning (ICML) 2023, 2023
302023
RATT: Leveraging Unlabeled Data to Guarantee Generalization
S Garg, S Balakrishnan, JZ Kolter, ZC Lipton
International Conference on Machine Learning (ICML) 2021, Oral, 2021
282021
Dual Language Models for Code Mixed Speech Recognition
S Garg, T Parekh, P Jyothi
Proceedings of Interspeech 2018 (19th Annual Conference of ISCA), 2018
23*2018
Downstream datasets make surprisingly good pretraining corpora
K Krishna, S Garg, JP Bigham, ZC Lipton
Association for Computational Linguistics (ACL), 2023, 2022
222022
Deconstructing distributions: A pointwise framework of learning
G Kaplun, N Ghosh, S Garg, B Barak, P Nakkiran
International Conference on Learning Representations (ICLR) 2023, 2022
222022
Tic-clip: Continual training of clip models
S Garg, M Farajtabar, H Pouransari, R Vemulapalli, S Mehta, O Tuzel, ...
arXiv preprint arXiv:2310.16226, 2023
192023
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
A Setlur, S Garg, X Geng, N Garg, V Smith, A Kumar
arXiv preprint arXiv:2406.14532, 2024
172024
Estimating uncertainty in MRF-based image segmentation: A perfect-MCMC approach
SP Awate, S Garg, R Jena
Medical image analysis (MedIA) 55, 181-196, 2019
152019
On Proximal Policy Optimization's Heavy-tailed Gradients
S Garg, J Zhanson, E Parisotto, A Prasad, JZ Kolter, S Balakrishnan, ...
International Conference on Machine Learning 139 (38), 3598-3609, 2021
132021
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
S Garg, A Setlur, ZC Lipton, S Balakrishnan, V Smith, A Raghunathan
Advances in Neural Information Processing Systems (NeurIPS), 2023, 2023
122023
Pixtral 12B
P Agrawal, S Antoniak, EB Hanna, B Bout, D Chaplot, J Chudnovsky, ...
arXiv preprint arXiv:2410.07073, 2024
92024
The system can't perform the operation now. Try again later.
Articles 1–20