Sotabase

Career

· Researcher, OpenAI2024–
· PhD Student, UC Berkeley EECS Department2019–2024

Publications (49)

Theoretically Principled Trade-off between Robustness and Accuracy
International Conference on Machine Learning · 2019
2,877
cited
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Neural Information Processing Systems · 2020
233
cited
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
International Conference on Machine Learning · 2020
216
cited
ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
arXiv.org · 2021
142
cited
Learning One-hidden-layer ReLU Networks via Gradient Descent
International Conference on Artificial Intelligence and Statistics · 2018
139
cited
White-Box Transformers via Sparse Rate Reduction
Neural Information Processing Systems · 2023
122
cited
Trading Inference-Time Compute for Adversarial Robustness
arXiv.org · 2025
52
cited
Predicting Out-of-Distribution Error with the Projection Norm
International Conference on Machine Learning · 2022
51
cited
Boundary thickness and robustness in learning models
Neural Information Processing Systems · 2020
47
cited
OpenAI GPT-5 System Card
2025
46
cited
Data Poisoning Attacks on Multi-Task Relationship Learning
AAAI Conference on Artificial Intelligence · 2018
45
cited
Federated Conformal Predictors for Distributed Uncertainty Quantification
International Conference on Machine Learning · 2023
37
cited
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
International Conference on Machine Learning · 2018
36
cited
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
Neural Information Processing Systems · 2022
33
cited
CTRL: Closed-Loop Transcription to an LDR via Minimaxing Rate Reduction
Entropy · 2021
32
cited
Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Mathematical and Scientific Machine Learning · 2020
31
cited
Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization
International Conference on Artificial Intelligence and Statistics · 2021
28
cited
On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging
International Conference on Artificial Intelligence and Statistics · 2021
28
cited
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
arXiv.org · 2024
27
cited
White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?
arXiv.org · 2023
27
cited
Sotabase
Yaodong Yu | Researcher Profile | Sotabase | Sotabase