Urmăriți
Ruiqi Zhang
Ruiqi Zhang
Ph.D. Student, Statistics Department at University of California, Berkeley
Adresă de e-mail confirmată pe berkeley.edu - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Trained transformers learn linear models in-context
R Zhang, S Frei, PL Bartlett
Journal of Machine Learning Research 25 (49), 1-55, 2024
982024
Off-policy fitted q-evaluation with differentiable function approximators: Z-estimation and inference theory
R Zhang, X Zhang, C Ni, M Wang
International Conference on Machine Learning, 26713-26749, 2022
182022
Negative preference optimization: From catastrophic collapse to effective unlearning
R Zhang, L Lin, Y Bai, S Mei
The First Conference of Language Models (COLM) in 2024, 2024
172024
AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition
Z Chen, Z Zhao, Z Zhu, R Zhang, X Li, B Raj, H Yao
NAACL 2024, 2024
52024
Optimal estimation of policy gradient via double fitted iteration
C Ni, R Zhang, X Ji, X Zhang, M Wang
International Conference on Machine Learning, 16724-16783, 2022
5*2022
Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
R Zhang, A Zanette
Advances in Neural Information Processing Systems, 2024, 2023
42023
In-context learning of a linear Transformer block: benefits of the MLP component and one-step GD initialization
R Zhang, J Wu, PL Bartlett
arXiv preprint arXiv:2402.14951, 2024
32024
Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement
R Zhang, Y Zhai, A Zanette
arXiv preprint arXiv:2402.15703, 2024
2024
Accelerating Best-of-N via Speculative Rejection
R Zhang, M Haider, M Yin, J Qiu, M Wang, P Bartlett, A Zanette
2nd Workshop on Advancing Neural Network Training: Computational Efficiency …, 0
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–9