Detecting pretraining data from large language models W Shi, A Ajith, M Xia, Y Huang, D Liu, T Blevins, D Chen, L Zettlemoyer arXiv preprint arXiv:2310.16789, 2023 | 106 | 2023 |
Private convex optimization via exponential mechanism S Gopi, YT Lee, D Liu COLT 2022, 2022 | 49 | 2022 |
Private non-smooth erm and sco in subquadratic steps J Kulkarni, YT Lee, D Liu Advances in Neural Information Processing Systems 34, 4053-4064, 2021 | 46* | 2021 |
When Does Differentially Private Learning Not Suffer in High Dimensions? X Li, D Liu, T Hashimoto, HA Inan, J Kulkarni, YT Lee, AG Thakurta Neurips 2022, 2022 | 43 | 2022 |
Super-resolution and robust sparse continuous fourier transform in any constant dimension: Nearly linear time and sample complexity Y Jin, D Liu, Z Song Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms …, 2023 | 18* | 2023 |
Pandora box problem with nonobligatory inspection: Hardness and approximation scheme H Fu, J Li, D Liu Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 789-802, 2023 | 12* | 2023 |
NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models Y Huang, D Liu, Z Zhong, W Shi, YT Lee arXiv preprint arXiv:2302.10879, 2023 | 11 | 2023 |
Algorithms and Adaptivity Gaps for Stochastic -TSP H Jiang, J Li, D Liu, S Singla ITCS 2020, 2019 | 11 | 2019 |
Private Convex Optimization in General Norms S Gopi, YT Lee, D Liu, R Shen, K Tian SODA 2023, 2022 | 10 | 2022 |
Algorithmic aspects of the log-Laplace transform and a non-Euclidean proximal sampler S Gopi, YT Lee, D Liu, R Shen, K Tian COLT 2023, 2023 | 9 | 2023 |
Resqueing parallel and private stochastic convex optimization Y Carmon, A Jambulapati, Y Jin, YT Lee, D Liu, A Sidford, K Tian FOCS 2023, 2023 | 9 | 2023 |
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks D Liu, A Ganesh, S Oh, A Guha Thakurta Advances in Neural Information Processing Systems 36, 2024 | 7* | 2024 |
Better Private Algorithms for Correlation Clustering D Liu COLT 2022, 2022 | 7 | 2022 |
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation Z Wang, Y Wu, F Liu, D Liu, L Hou, H Yu, J Li, H Ji ICLR 2023, 2022 | 5 | 2022 |
User-level differentially private stochastic convex optimization: Efficient algorithms with optimal rates D Liu, H Asi International Conference on Artificial Intelligence and Statistics, 4240-4248, 2024 | 4 | 2024 |
Lower Bounds for Differentially Private ERM: Unconstrained and Non-Euclidean D Liu, Z Lu arXiv preprint arXiv:2105.13637, 2021 | 3* | 2021 |
Private gradient descent for linear regression: Tighter error bounds and instance-specific uncertainty estimation G Brown, K Dvijotham, G Evans, D Liu, A Smith, A Thakurta arXiv preprint arXiv:2402.13531, 2024 | 2 | 2024 |
The Convergence Rate of SGD's Final Iterate: Analysis on Dimension Dependence D Liu, Z Lu arXiv preprint arXiv:2106.14588, 2021 | 2 | 2021 |
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning L Chua, B Ghazi, Y Huang, P Kamath, D Liu, P Manurangsi, A Sinha, ... arXiv preprint arXiv:2406.14322, 2024 | | 2024 |
Private Online Learning via Lazy Algorithms H Asi, T Koren, D Liu, K Talwar arXiv preprint arXiv:2406.03620, 2024 | | 2024 |