Publications
Google Scholar Profile
Preprints
- Y. Bu*, G. Aminian*, L. Toni, M. R. D. Rodrigues, G. W. Wornell. “An Exact Characterization of the Generalization Error for the Gibbs Algorithm,” (* equal contribution), submitted to IEEE Transactions on Information Theory, preliminary version appeared in NeurIPS 2021.
- A. Weiss, A. Lancho, Y. Bu, G. W. Wornell. “A Bilateral Bound on the Mean Squared Error for Estimation in Model Mismatch,” submitted to IEEE Signal Processing Letter, Jul 2022.
- M. Shen, Y. Bu, P. Sattigeri, S. Ghosh, S. Das, G. W. Wornell. “Post-hoc Uncertainty Learning using a Dirichlet Meta-Model,” submitted to Conference on Neural Information Processing Systems (NeurIPS 2022), May 2022.
- M. Shen, Y. Bu, G. W. Wornell. “On the Benefits of Selectivity in Pseudo-Labeling for Unsupervised Multi-Source-Free Domain Adaptation,” submitted to Conference on Neural Information Processing Systems (NeurIPS 2022), May 2022.
- Y. Bu, J. Lu, V. V. Veeravalli. “Active and Adaptive Sequential learning,” arXiv preprint, 2020.
Journal Publications
- Y. Bu*, J. K. Lee*, P. Sattigeri, R. Panda, G. W. Wornell, L. Karlinsky, R. Feris. “A Maximal Correlation Framework for Fair Machine Learning,” (* equal contribution), Entropy 24, no. 4, pp. 461, Mar. 2022.
- Y. Bu, W. Gao, S. Zou, V. V. Veeravalli. “Population Risk Improvement with Model Compression: An Information-Theoretic Approach,” Entropy 23, no. 10, pp. 1255, Sept. 2021.
- Y. Bu, S. Zou, V. V. Veeravalli. “Tightening Mutual Information Based Bounds on Generalization Error,” IEEE Journal on Selected Areas in Information Theory, vol. 1, pp. 121 – 130, May 2020.
- C. Wilson, Y. Bu, V. V. Veeravalli. “Adaptive Sequential Machine Learning,” Sequential Analysis, vol. 38, no. 4, Oct. 2019.
- Y. Bu, S. Zou, V. V. Veeravalli. “Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection,” IEEE Transactions on Signal Processing, vol. 67, no. 8, pp. 2115-2128, Apr. 2019.
- Y. Bu*, S. Zou*, Y. Liang, V. V. Veeravalli. “Estimation of KL Divergence: Optimal Minimax Rate,” (*equal contribution), IEEE Transactions on Information Theory, vol. 64, no. 4, pp. 2648-2674, Apr. 2018.
Code available at Github
Conference Publications
- A. Lancho, A. Weiss, G. Lee, J. Tang, Y. Bu, Y. Polyanskiy, G. W. Wornell. “Data-Driven Blind Synchronization and Interference Rejection for Digital Communication Signals,” to appear in, IEEE Global Communications Conference, Dec. 2022.
- G. Lee, A. Weiss, A. Lancho, J. Tang, Y. Bu, Y. Polyanskiy, G. W. Wornell. “Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separation,” to appear in, IEEE International Workshop on Machine Learning for Signal Processing, Aug. 2022.
- A. Shah*, Y. Bu*, J. K. Lee, P. Sattigeri, R. Panda, S. Das, G. W. Wornell. “Selective Regression under Fairness Criteria,” (* equal contribution), International Conference on Machine Learning (ICML), Jul. 2022. (acceptance rate: 22%)
- G. Aminian*, Y. Bu*, G. W. Wornell, M. R. D. Rodrigues. “Tighter Expected Generalization Error Bounds via Convexity of Information Measures,” (* equal contribution), IEEE International Symposium on Information Theory (ISIT), Jun. 2022.
- Y. Bu*, J. K. Lee*, P. Sattigeri, R. Panda, G. W. Wornell, L. Karlinsky, R. Feris. “A Maximal Correlation Approach to Imposing Fairness in Machine Learning,” (*equal contribution), IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022.
- Y. Bu*, G. Aminian*, L. Toni, M. R. D. Rodrigues, G. W. Wornell. “Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm,” (* equal contribution), International Conference on Artificial Intelligence and Statistics (AISTATS), Mar. 2022. (acceptance rate: 29%)
- G. Aminian*, Y. Bu*, L. Toni, M. R. D. Rodrigues, G. W. Wornell. “An Exact Characterization of the Generalization Error for the Gibbs Algorithm,” (* equal contribution), Conference on Neural Information Processing Systems (NeurIPS), Dec. 2021. (acceptance rate: 26%)
- Y. Bu*, J. K. Lee*, D. Rajan, P. Sattigeri, R. Panda, S. Das, G. W. Wornell. “Fair Selective Classification via Sufficiency,” (* equal contribution), International Conference on Machine Learning (ICML), Jul. 2021. (Oral, Top 3%)
- G. Aminian*, Y. Bu*, L. Toni, M. Rodrigues, G. W. Wornell. “Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information,” (* equal contribution), ICML Workshop on Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning, Jul. 2021.
- Y. Bu, T. Wang, G. W. Wornell. “SDP Methods for Sensitivity-Constrained Privacy Funnel and Information Bottleneck Problems,” IEEE International Symposium on Information Theory (ISIT), Melbourne, Australia, Jul. 2021.
- Y. Bu, W. Gao, S. Zou, V. V. Veeravalli. “Information-theoretic Understanding of Population Risk Improvement with Model Compression,” AAAI Conference on Artificial Intelligence (AAAI), New York, Feb. 2020. (acceptance rate: 21%)
- Y. Bu, K. Small. “Active Learning in Recommendation Systems with Multi-level User Preferences,” AAAI Workshop on Interactive and Conversational Recommendation Systems (WICRS), New York, Feb. 2020.
- Y. Bu, J. Lu, V. V. Veeravalli. “Active and Adaptive Sequential Learning with Per Time-step Excess Risk Guarantees,” IEEE Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2019.
- Y. Bu, S. Zou, V. V. Veeravalli. “Tightening Mutual Information Based Bounds on Generalization Error,” IEEE International Symposium on Information Theory (ISIT), Paris, France, Jul. 2019.
- Y. Bu, J. Lu, V. V. Veeravalli. “Model Change Detection with Application to Machine Learning,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 2019.
- Y. Bu, S. Zou, V. V. Veeravalli. “Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection,” IEEE International Symposium on Information Theory (ISIT), Aachen, Germany, Jun. 2017.
- Y. Bu, S. Zou, Y. Liang, V. V. Veeravalli. “Estimation of KL Divergence between Large-Alphabet Distributions,” IEEE International Symposium on Information Theory (ISIT), Barcelona, Spain, Jul. 2016.
- Y. Bu, S. Zou, Y. Liang, V. V. Veeravalli. “Universal Outlying Sequence Detection for Continuous Observations,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, Mar. 2016