| The split Bregman method for L1-regularized problems T Goldstein, S Osher SIAM journal on imaging sciences 2 (2), 323-343, 2009 | 5336 | 2009 |
| Visualizing the loss landscape of neural nets H Li, Z Xu, G Taylor, C Studer, T Goldstein Advances in neural information processing systems 31, 2018 | 2386 | 2018 |
| Adversarial training for free! A Shafahi, M Najibi, MA Ghiasi, Z Xu, J Dickerson, C Studer, LS Davis, ... Advances in neural information processing systems 32, 2019 | 1646 | 2019 |
| Poison frogs! targeted clean-label poisoning attacks on neural networks A Shafahi, WR Huang, M Najibi, O Suciu, C Studer, T Dumitras, ... Advances in neural information processing systems 31, 2018 | 1338 | 2018 |
| Fast alternating direction optimization methods T Goldstein, B O'Donoghue, S Setzer, R Baraniuk SIAM Journal on Imaging Sciences 7 (3), 1588-1623, 2014 | 962 | 2014 |
| A watermark for large language models J Kirchenbauer, J Geiping, Y Wen, J Katz, I Miers, T Goldstein International Conference on Machine Learning, 17061-17084, 2023 | 710 | 2023 |
| Geometric applications of the split Bregman method: segmentation and surface reconstruction T Goldstein, X Bresson, S Osher Journal of scientific computing 45, 272-293, 2010 | 600 | 2010 |
| Freelb: Enhanced adversarial training for natural language understanding C Zhu, Y Cheng, Z Gan, S Sun, T Goldstein, J Liu arXiv preprint arXiv:1909.11764, 2019 | 548 | 2019 |
| Certified data removal from machine learning models C Guo, T Goldstein, A Hannun, L Van Der Maaten arXiv preprint arXiv:1911.03030, 2019 | 498 | 2019 |
| Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses M Goldblum, D Tsipras, C Xie, X Chen, A Schwarzschild, D Song, ... IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (2), 1563-1580, 2022 | 393* | 2022 |
| Are adversarial examples inevitable? A Shafahi, WR Huang, C Studer, S Feizi, T Goldstein International Conference on Learning Representations, 2019 | 387 | 2019 |
| A cookbook of self-supervised learning R Balestriero, M Ibrahim, V Sobal, A Morcos, S Shekhar, T Goldstein, ... arXiv preprint arXiv:2304.12210, 2023 | 380 | 2023 |
| Transferable clean-label poisoning attacks on deep neural nets C Zhu, WR Huang, H Li, G Taylor, C Studer, T Goldstein International conference on machine learning, 7614-7623, 2019 | 370 | 2019 |
| Quantized precoding for massive MU-MIMO S Jacobsson, G Durisi, M Coldrey, T Goldstein, C Studer IEEE Transactions on Communications 65 (11), 4670-4684, 2017 | 366 | 2017 |
| Baseline defenses for adversarial attacks against aligned language models N Jain, A Schwarzschild, Y Wen, G Somepalli, J Kirchenbauer, P Chiang, ... arXiv preprint arXiv:2309.00614, 2023 | 354* | 2023 |
| Saint: Improved neural networks for tabular data via row attention and contrastive pre-training G Somepalli, M Goldblum, A Schwarzschild, CB Bruss, T Goldstein arXiv preprint arXiv:2106.01342, 2021 | 354 | 2021 |
| Training neural networks without gradients: A scalable admm approach G Taylor, R Burmeister, Z Xu, B Singh, A Patel, T Goldstein International conference on machine learning, 2722-2731, 2016 | 335 | 2016 |
| Making an invisibility cloak: Real world adversarial attacks on object detectors Z Wu, SN Lim, LS Davis, T Goldstein Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 | 330 | 2020 |
| Convex phase retrieval without lifting via PhaseMax T Goldstein, C Studer International Conference on Machine Learning, 1273-1281, 2017 | 324* | 2017 |
| Test-time prompt tuning for zero-shot generalization in vision-language models M Shu, W Nie, DA Huang, Z Yu, T Goldstein, A Anandkumar, C Xiao Advances in Neural Information Processing Systems 35, 14274-14289, 2022 | 321 | 2022 |
Micah GoldblumColumbia UniversityVerified email at columbia.edu
