Yuheng Bu's Homepage
 |
Yuheng BuAssistant Professor Contact InformationEmail: buyuheng [at] {ufl} [dot] edu |
Biography
I am an Assistant Professor in the Department of Electrical & Computer Engineering (ECE) at University of Florida.
Before joining the University of Florida, I was a postdoctoral research associate at the Research Laboratory of Electronics and Institute for Data, Systems, and Society (IDSS), Massachusetts Institute of Technology (MIT). I received my Ph.D. degree at the Coordinated Science Laboratory and the Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign (UIUC) in 2019. Before that, I received a B.S. degree (with honors) in Electronic Engineering from Tsinghua University in 2014.
Research
My research interests lie in the intersection of machine learning, information theory and signal processing. I leverage the tools from information theory and signal processing to develop theoretically justified learning algorithms for diverse applications, including watermarking generative AI, fair machine learning, uncertainty quantification, model compression.
More broadly, the primary goal of my research is to lay information-theoretic foundations for trustworthy learning algorithms, particularly with generalization, fairness, and robustness guarantees.
To Prospective Students
PhD candidates: Self-motivated students with strong backgrounds in probability, statistics, machine learning, and information theory are welcome to reach out. You should be comfortable with writing and reading proofs and learning challenging new mathematical concepts; in other words, a decent mathematical maturity is required.
Please send me an email with the subject “Prospective Ph.D. Student” attached with your academic CV and undergraduate/graduate transcripts.
Selected Publications
Y. Liu, Y. Bu. “Adaptive Text Watermark for Large Language Models” International Conference on Machine Learning (ICML), Jul. 2024.
M. Shen, Y. Bu, G. W. Wornell. “On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation,” International Conference on Machine Learning (ICML), Jul. 2023.
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.
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), 2021.
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. (Long Talk, Top 3%)
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.
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.
News
Sep 2024, our paper, “Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?” has been accepted by NeurIPS 2024 (acceptance rate: 26%)!
July 2024, our paper, “Information-theoretic Analysis of the Gibbs Algorithm: An Individual Sample Approach,” have been accepted by ITW 2024. Additionally, we will organize a tutorial at ITW 2024 titled “Characterizing the Generalization Error of Machine Learning Algorithms Via Information Measures.” Stay tuned!
June 2024, our paper, “Learning Orthonormal Features in Self-Supervised Learning using Functional Maximal Correlation,” has been accepted by ICIP 2024.
May 2024, two papers accepted at ICML 2024 (acceptance rate: 28%)!
The first paper, “Adaptive Text Watermark for Large Language Models” proposes a watermarking technique that distinguishes AI/human-generated text. This is Yepeng's first paper since he joined the group! Congrats!
The second paper, “Operator SVD with Neural Networks via Nested Low-Rank Approximation,” proposes a new optimization framework that can train neural networks to learn the top singular functions of a given operator.
Apr 2024, our paper, “Information-Theoretic Opacity-Enforcement in Markov Decision Processes,” has been accepted by IJCAI 2024.
Apr 2024, two papers, “Towards Optimal Inverse Temperature in the Gibbs Algorithm” and “Group Fairness with Uncertain Sensitive Attributes,” have been accepted by ISIT 2024.
March 2024, I presented our paper “Adaptive Text Watermark for Large Language Models” at Annual Conference on Information Science and Systems (CISS), Princeton, NJ.
Jan 2024, I have co-organized the 7th Annual Workshop on Cognition & Control together with Prof. Sean Meyn, Prof. Jie Fu at UF Reitz Union. Talks include topics such as reinforcement learning, accelerated optimization, information theory, brain-machine interface systems, and much more!
Jan 2024, our paper, “Gibbs-Based Information Criteria and the Over-Parameterized Regime” has been accepted by AISTATS 2024 (acceptance rate: 28%)! This is my student Haobo's first paper, Congrats to Haobo!
Oct 2023, our paper, “Information-theoretic Characterizations of Generalization Error for the Gibbs Algorithm” has been accepted for publication on IEEE Transactions on Information Theory.
Sep 2023, I gave an invited talk on “Group Fairness with Uncertainty in Sensitive Attributes” at Allerton Conference on Comminication, Control and Computing, Monticello, IL.
Aug 2023, the video recordings of the 6th Annual Workshop on Cognition & Control are now available on Youtube!
Apr 2023, our paper, “On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation,” has been accepted by ICML 2023 (acceptance rate: 28%).
Apr 2023, two papers, “On the Generalization Error of Meta Learning for the Gibbs Algorithm” and “A Bilateral Bound on the Mean Squared Error for Estimation in Model Mismatch,” have been accepted by ISIT 2023.
Feb 2023, my collaborators and I were interviewed with MIT News for our recent AAAI publication “Post-hoc Uncertainty Learning using a Dirichlet Meta-Model.” Check out here!
Feb 2023, I gave a talk on “Characterizing the generalization error of Gibbs algorithms using information measures” at Information Theory and Applications Workshop, ITA 2023, San Diego.
Jan 2023, our paper, “Adaptive Sequential Machine Learning,” has been selected as the winner of the 16th Abraham Wald Prize in Sequential Analysis!
Jan 2023, I have co-organized the 6th Annual Workshop on Cognition & Control together with Prof. Sean Meyn, Prof. Shreya Saxena at UF Reitz Union. Talks include topics such as reinforcement learning, accelerated optimization, information theory, brain-machine interface systems, and much more!
Jan 2023, I gave a virtual presentation “From Sensitivity-constrained Information Bottleneck to Fair Selective Prediction” at Information Theory and Data Science Workshop organized by National University of Singapore.