Seuraa
Rohith Kuditipudi
Rohith Kuditipudi
Vahvistettu sähköpostiosoite verkkotunnuksessa stanford.edu - Kotisivu
Nimike
Viittaukset
Viittaukset
Vuosi
On the opportunities and risks of foundation models
R Bommasani, DA Hudson, E Adeli, R Altman, S Arora, S von Arx, ...
arXiv preprint arXiv:2108.07258, 2021
47882021
Robust distortion-free watermarks for language models
R Kuditipudi, J Thickstun, T Hashimoto, P Liang
arXiv preprint arXiv:2307.15593, 2023
1372023
Explaining landscape connectivity of low-cost solutions for multilayer nets
R Kuditipudi, X Wang, H Lee, Y Zhang, Z Li, W Hu, R Ge, S Arora
Advances in neural information processing systems 32, 2019
992019
Learning two-layer neural networks with symmetric inputs
R Ge, R Kuditipudi, Z Li, X Wang
arXiv preprint arXiv:1810.06793, 2018
702018
A pretty fast algorithm for adaptive private mean estimation
R Kuditipudi, J Duchi, S Haque
The Thirty Sixth Annual Conference on Learning Theory, 2511-2551, 2023
30*2023
Minimizing the number of detrimental objects in multi-dimensional graph-based codes
A Hareedy, R Kuditipudi, R Calderbank
IEEE Transactions on Communications 68 (9), 5299-5312, 2020
252020
Memorize to generalize: on the necessity of interpolation in high dimensional linear regression
C Cheng, J Duchi, R Kuditipudi
Conference on Learning Theory, 5528-5560, 2022
12*2022
Resampling methods for private statistical inference
K Chadha, J Duchi, R Kuditipudi
arXiv preprint arXiv:2402.07131, 2024
5*2024
Two fundamental limits for uncertainty quantification in predictive inference
F Areces, C Cheng, J Duchi, K Rohith
The Thirty Seventh Annual Conference on Learning Theory, 186-218, 2024
12024
Independence Tests for Language Models
S Zhu, A Ahmed, R Kuditipudi, P Liang
arXiv preprint arXiv:2502.12292, 2025
2025
Auditing Prompt Caching in Language Model APIs
C Gu, XL Li, R Kuditipudi, P Liang, T Hashimoto
arXiv preprint arXiv:2502.07776, 2025
2025
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–11