Sotabase

Career

· CEO & Co-founder, Nexusflow2023–
· Director of Research & Distinguished Scientist, NVIDIA2023–
· Assistant Professor, University of California, Berkeley2018–
· Doctor of Philosophy (Ph.D.), Stanford University2012–2018
· Ph.D. in Electrical Engineering, Stanford University2012–2018
· Co-founder, Nexusflow.ai
· PhD in Computer Science, Stanford University
· Bachelor's Degree in Electronic Engineering, Tsinghua University

Publications (106)

Theoretically Principled Trade-off between Robustness and Accuracy
International Conference on Machine Learning · 2019
2,877
cited
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
IEEE Transactions on Information Theory · 2021
316
cited
Minimax Estimation of Functionals of Discrete Distributions
IEEE Transactions on Information Theory · 2014
263
cited
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
International Conference on Machine Learning · 2023
254
cited
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Conference on Empirical Methods in Natural Language Processing · 2024
162
cited
Jump-Start Reinforcement Learning
International Conference on Machine Learning · 2022
145
cited
Universal Estimation of Directed Information
IEEE Transactions on Information Theory · 2010
137
cited
Toward the Fundamental Limits of Imitation Learning
Neural Information Processing Systems · 2020
108
cited
Maximum Likelihood Estimation of Functionals of Discrete Distributions
IEEE Transactions on Information Theory · 2014
107
cited
Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning
IACR Cryptology ePrint Archive · 2021
103
cited
Optimal rates of entropy estimation over Lipschitz balls
Annals of Statistics · 2017
75
cited
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
arXiv.org · 2023
71
cited
Minimax estimation of the L1 distance
International Symposium on Information Theory · 2016
68
cited
Minimax Estimation of Discrete Distributions under ℓ1 Loss
arXiv.org · 2014
64
cited
Justification of Logarithmic Loss via the Benefit of Side Information
IEEE Transactions on Information Theory · 2014
61
cited
The Sample Complexity of Online Contract Design
ACM Conference on Economics and Computation · 2022
61
cited
Concentration Inequalities for the Empirical Distribution
Information and Inference A Journal of the IMA · 2018
58
cited
Dependence measures bounding the exploration bias for general measurements
International Symposium on Information Theory · 2016
55
cited
Deconstructing Generative Adversarial Networks
IEEE Transactions on Information Theory · 2019
53
cited
Generalized Resilience and Robust Statistics
Annals of Statistics · 2019
53
cited
Sotabase
Jiantao Jiao | Researcher Profile | Sotabase | Sotabase