Publications

W. Li, Z. Liu, Y. Yu, B. Low (2026). Nonlinear Axiomatic Attribution for Cooperative Games. Forty-Second Annual Conference on Uncertainty in Artificial Intelligence (UAI).
URL PDF Code
W. Li, Y. Yu, B. Low (2026). Provably Adaptive Linear Approximation for the Shapley Value and Beyond. International Conference on Machine Learning (ICML).
URL PDF Code
H. Lu, D. Lo, Y. Yu (2026). SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF Code Poster
D. Liao, F. Dangel, Y. Yu (2026). Efficient Bilevel Optimization with KFAC-Based Hypergradients. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF Code
W. Li, Y. Yu, B. Low (2026). TreeGrad-Ranker: Feature Ranking via O(L)-Time Gradients for Decision Trees. International Conference on Learning Representations (ICLR).
URL PDF Code
H. Lu, Y. Yu, D. Lo (2026). SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples. International Conference on Learning Representations (ICLR).
URL PDF Code Poster
J. Di, Y. Lu, Y. Yu, G. Kamath, A. Dziedzic, F. Boenisch (2026). Demystifying Foreground-Background Memorization in Diffusion Models. Association for the Advancement of Artificial Intelligence (AAAI).
URL PDF
J. Dong, B. Wang, Y. Yu (2025). Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code Poster
A. Kassis, U. Hengartner, Y. Yu (2025). DiffBreak: Is Diffusion-Based Purification Robust?. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code Poster Slides
Y. Wang, Y. Lu, X.-S. Gao, G. Kamath, Y. Yu (2025). BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code Poster
W. Duan, Y. Yu, J. He, Y. Shi (2025). Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code Poster
Y. Wang, Y. Lu, G. Zhang, F. Boenisch, A. Dziedzic, Y. Yu, X.-S. Gao (2025). MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation. Transactions on Machine Learning Research (TMLR).
URL PDF Code
R. Jin, X. Li, Y. Yu, B. Wang (2025). A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD. International Conference on Machine Learning (ICML).
URL PDF
H. Lu, Q. Wu, Y. Yu (2025). Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets. International Conference on Machine Learning (ICML).
URL PDF Code
Z. Hu, Y. Yu (2025). Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization. International Conference on Learning Representations (ICLR).
URL PDF Code
H. Lu, S. Szabados, Y. Yu (2025). Diffusion Models under Group Transformations. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF Code
J. Dong, B. Wang, Y. Yu (2025). Last-iterate Convergence in Regularized Graphon Mean Field Game. Association for the Advancement of Artificial Intelligence (AAAI).
URL PDF
Y. Lu, M. Yang, Z. Liu, G. Kamath, Y. Yu (2024). Disguised Copyright Infringement of Latent Diffusion Models. International Conference on Machine Learning (ICML).
URL PDF Code
S. Malekmohammadi, Y. Yu, Y. Cao (2024). Noise-Aware Aggregation for Heterogeneous Differentially Private Federated Learning. International Conference on Machine Learning (ICML).
URL PDF
Y. Lu, M. Yang, G. Kamath, Y. Yu (2024). Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors. 2nd IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).
URL PDF
J. Dong, B. Wang, Y. Yu (2024). Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF Code
W. Li, Y. Yu (2024). Faster Approximation of Probabilistic and Distributional Values via Least Squares. International Conference on Learning Representations (ICLR).
URL PDF Code
W. Li, Y. Yu (2024). One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code
W. Li, Y. Yu (2023). Robust Data Valuation with Weighted Banzhaf Values. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code
Y. Lu, Y. Yu, X. Li, V. P. Nia (2023). Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
A. Ghose, A. Gupta, Y. Yu, P. Poupart (2023). Batchnorm Allows Unsupervised Radial Attacks. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Lu, G. Zhang, S. Sun, H. Guo, Y. Yu (2023). $f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning. Transactions on Machine Learning Research.
URL PDF
W. Li, L. Kari, Y. Yu, L. Hug (2023). MT-MAG: Accurate and interpretable machine learning for complete or partial taxonomic assignments of metagenome-assembled genomes. PLOS One.
URL PDF
H. Lu, Y. Lu, D. Jiang, S. Szabados, S. Sun, Y. Yu (2023). CM-GAN: Stabilizing GAN Training with Consistency Models. ICML Workshop on Structured Probabilistic Inference & Generative Modeling.
URL PDF
Y. Lu, G. Kamath, Y. Yu (2023). Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks. International Conference on Machine Learning (ICML).
URL PDF Code
D. Jiang, S. Sun, Y. Yu (2023). Functional Rényi Differential Privacy for Generative Modeling. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
J. Xin, R. Tang, Z. Jiang, Y. Yu, J. Lin (2023). Operator Selection and Ordering in a Pipeline Approach to Efficiency Optimizations for Transformers. Findings of the Association for Computational Linguistics (ACL).
URL PDF
Tim Dockhorn, Robin Rombach, Andreas Blatmann, Yaoliang Yu (2023). Distilling the Knowledge in Diffusion Models. CVPR workshop on Generative Models for Computer Vision.
URL PDF
H. Lu, D. Herman, Y. Yu (2023). Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality. International Conference on Learning Representations (ICLR).
URL PDF
G. Zhang, S. Malekmohammadi, Xi Chen, Y. Yu (2023). Proportional Fairness in Federated Learning. Transactions on Machine Learning Research.
URL PDF
Y. Lu, G. Kamath, Y. Yu (2022). Indiscriminate Data Poisoning Attacks on Neural Networks. Transactions on Machine Learning Research.
URL PDF Code
S. Malekmohammadi, K. Shaloudegi, Z. Hu, Y. Yu (2022). A Unifying Framework for Federated Learning. Federated and Transfer Learning.
URL PDF
T. Fujiwara, J. Zhao, F. Chen, Y. Yu, Kwan-Liu Ma (2022). Network Comparison with Interpretable Contrastive Network Representation Learning. Journal of Data Science, Statistics, and Visualisation.
URL PDF
Z. Hu, K. Shaloudegi, G. Zhang, Y. Yu (2022). FedMGDA+: Federated Learning meets Multi-objective Optimization. IEEE Transactions on Network Science and Engineering.
URL PDF
D. Jiang, S. Sun, Y. Yu (2022). Revisiting flow generative models for Out-of-distribution detection. International Conference on Learning Representations (ICLR).
URL PDF Code
J. Sun, D. Jiang, Y. Yu (2022). Conditional Generative Quantile Networks via Optimal Transport. ICLR Workshop on Deep Generative Models for Highly Structured Data.
URL PDF
G. Zhang, P. Poupart, Y. Yu (2022). Optimality and Stability in Non-Convex Smooth Games. Journal of Machine Learning Research.
URL PDF
X. Li, B. Liu, Y. Yu, W. Liu, C. Xu, V. Nia (2021). S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
G. Zhang, H. Zhao, Y. Yu, P. Poupart (2021). Quantifying and Improving Transferability in Domain Generalization. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code
T. Dockhorn, Y. Yu, E. Sari, M. Zolnouri, V. Nia (2021). Demystifying and Generalizing BinaryConnect. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
S. Qian, H. Pham, T. Lutellier, Z. Hu, J. Kim, T. Lin, Y. Yu, J. Chen, S. Shah (2021). Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF Code
J. Xin, R. Tang, Y. Yu, J. Lin (2021). The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing. The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP).
URL PDF Code
G. Zhang, K. Wu, P. Poupart, Y. Yu (2021). Newton-type Methods for Minimax Optimization. ICML Workshop on Beyond First-Order Methods in ML Systems.
URL PDF Code
H. Cheng, X. Liu, L. Pereira, Y. Yu, J. Gao (2021). Posterior Differential Regularization with $f$-divergence for Improving Model Robustness. Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL).
URL PDF
J. Xin, R. Tang, Y. Yu, J. Lin (2021). BERxiT: Better-fine-tuned and Wider-applicable Early Exit for *BERT. The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL).
URL PDF Code
H. Pham, S. Qian, J. Wang, T. Lutellier, J. Rosenthal, L. Tan, Y. Yu, N. Nagappan (2021). Problems and Opportunities in Training Deep-Learning Software Systems: An Analysis of Variance. 35th IEEE/ACM International Conference on Automated Software Engineering (ASE).
URL PDF Code
X. Lian, K. Jain, J. Truszkowski, P. Poupart, Y. Yu (2021). Unsupervised Multilingual Alignment using Wasserstein Barycenters. International Joint Conference on Artificial Intelligence (IJCAI).
URL PDF
J. Xin, R. Nogueira, Y. Yu, J. Lin (2020). Early Exiting BERT for Efficient Document Ranking. Proceedings of the First Workshop on Simple and Efficient Natural Language Processing (SustaiNLP 2020).
URL PDF Code
Yi Shi, Zehua Guo, Xianbin Su, Luming Meng, Mingxuan Zhang, Jing Sun, Chao Wu, Minhua Zheng, Xueyin Shang, Xin Zou, Wangqiu Cheng, Yaoliang Yu, Yujia Cai, Chaoyi Zhang, Weidong Cai, Lin-Tai Da, Guang He, Ze-Guang Han (2020). DeepAntigen: a novel method for neoantigen prioritization via 3D genome and deep sparse learning. Bioinformatics.
URL PDF Code
Yi Shi, Mingxuan Zhang, Luming Meng, Xianbin Su, Xueying Shang, Zehua Guo, Qingjiao Li, Mengna Lin, Xin Zou, Qing Luo, Yaoliang Yu, Yanting Wu, Lintai Da, Tom Weidong Cai, Guang He, Ze-Guang Han (2020). A novel neoantigen discovery approach based on chromatin high order conformation. BMC Med Genomics.
URL PDF
T. Dockhorn, J. Ritchie, Y. Yu, I. Murray (2020). Density Deconvolution with Normalizing Flows. ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models.
URL PDF
R. Tang, J. Lee, J. Xin, X. Liu, Y. Yu, J. Lin (2020). Showing Your Work Doesn't Always Work. Proceedings of the Association for Computational Linguistics (ACL).
URL PDF Code
J. Xin, R. Tang, J. Lee, Y. Yu, J. Lin (2020). DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. Proceedings of the Association for Computational Linguistics (ACL).
URL PDF Code
P. Jaini, I. Kobyzev, Y. Yu, M. Brubaker (2020). Tails of Lipschitz Triangular Flows. International Conference on Machine Learning (ICML).
URL PDF
K. Wu, W. Ding, R. Huang, Y. Yu (2020). On Minimax Optimality of GANs for Robust Mean Estimation. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF
Y. Ma, V. Ganapathiraman, Y. Yu, X. Zhang (2020). Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space. International Conference on Machine Learning (ICML).
URL PDF
K. Wu, H. Wang, Y. Yu (2020). Stronger and Faster Wasserstein Adversarial Attacks. International Conference on Machine Learning (ICML).
URL PDF Code
G. Zhang, Y. Yu (2019). Convergence of Gradient Methods on Bilinear Zero-Sum Games. International Conference on Learning Representations (ICLR).
URL PDF Code
K. Wu, Y. Yu (2019). Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin. NeurIPS Workshop on Maching Learning with Guarantees.
URL PDF Code Poster
S. Sun, Y. Yu (2019). Least-Squares Estimation of Weakly Convex Functions. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF
M. Marchetti-Bowick, Y. Yu, W. Wu, E. Xing (2019). A Penalized Regression Model for the Joint Estimation of eQTL Associations and Gene Network Structure. Annals of Applied Statistics.
URL PDF
J. Xin, J. Lin, Y. Yu (2019). What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP).
URL PDF
P. Jaini, K. Selby, Y. Yu (2019). Sum-of-squares Polynomial Flow. International Conference on Machine Learning (ICML).
URL PDF
J. Wang, S. Sun, Y. Yu (2019). Multivariate Triangular Quantile Maps for Novelty Detection. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
P. Xie, J. Kim, Q. Ho, Y. Yu, E. Xing (2018). Orpheus: Efficient Distributed Machine Learning via System and Algorithm Co-design. ACM Symposium on Cloud Computing (SoCC).
URL PDF
V. Ganapathiraman, Z. Shi, X. Zhang, Y. Yu (2018). Inductive Two-Layer Modeling with Parametric Bregman Transfer. International Conference on Machine Learning (ICML).
URL PDF
Y. Zhou, Y. Liang, Y. Yu, W. Dai, E. Xing (2018). Distributed Proximal Gradient Algorithm for Partially Asynchronous Computer Clusters. Journal of Machine Learning Research.
URL PDF
P. Jaini, P. Poupart, Y. Yu (2018). Deep Homogeneous Mixture Models: Representation, Separation and Approximation. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Z. Shi, X. Zhang, Y. Yu (2017). Bregman Divergence for Stochastic Variance Reduction Methods: Adversarial Prediction and Saddle-Point Problems. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
M. Law, Y. Yu, R. Urtasun, R. Zemel, E. Xing (2017). Efficient Multiple Instance Metric Learning using Weakly Supervised Data. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
URL PDF
J. Yin, Y. Yu (2017). Convex-constrained Sparse Additive Modeling and Its Extensions. Conference on Uncertainty in Artificial Intelligence (UAI).
URL PDF
X. Chang, Y. Yu, Y. Yang (2017). Robust Top-$k$ Multiclass SVM for Visual Category Recognition. ACM Conference on Knowledge Discovery and Data Mining (KDD).
URL PDF
P. Xie, Y. Deng, Y. Zhou, A. Kumar, Y. Yu, J. Zou, E. Xing (2017). Learning Latent Space Models with Angular Constraints. International Conference on Machine Learning (ICML).
URL PDF
Y. Zhou, K. Yuan, Y. Yu, X. Ni, P. Xie, E. Xing, S. Xu (2017). Inference of Multiple-wave Population Admixture by Modeling Decay of Linkage Disequilibrium With Polynomial Functions. Heredity.
URL PDF
X. Ma, Y. Gao, Z. Hu, Y. Yu, Y. Deng, E. Hovy (2017). Dropout with Expectation-Linear Regularization. International Conference on Learning Representations (ICLR).
URL PDF
Y. Yu, X. Zhang, D. Schuurmans (2017). Generalized Conditional Gradient for Sparse Estimation. Journal of Machine Learning Research (JMLR).
URL PDF
X. Chang, Y. Yu, Y. Yang, E. Xing (2016). They Are Not Equally Reliable: Semantic Event Search using Differentiated Concept Classifiers. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
URL PDF
M. Law, Y. Yu, M. Cord, E. Xing (2016). Closed-Form Training of Mahalanobis Distance for Supervised Clustering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
URL PDF
V. Ganapathiraman, X. Zhang, Y. Yu, J. Wen (2016). Convex Two-Layer Modeling with Latent Structure. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
X. Chang, Y. Yu, Y. Yang, E. Xing (2016). Semantic Pooling for Complex Event Analysis in Untrimmed Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence.
URL PDF
H. Cheng, Y. Yu, X. Zhang, E. Xing, D. Schuurmans (2016). Scalable and Sound Low-Rank Tensor Learning. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF
Y. Zhou, Y. Yu, W. Dai, Y. Liang, E. Xing (2016). On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel System. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF
K. Kandasamy, Y. Yu (2016). Additive Approximations in High Dimensional Nonparametric Regression via the SALSA. International Conference on Machine Learning (ICML).
URL PDF
P. Xie, J. Kim, Y. Zhou, Q. Ho, A. Kumar, Y. Yu, E. Xing (2016). Lighter-Communication Distributed Machine Learning via Sufficient Factor Broadcasting. Conference on Uncertainty in Artificial Intelligence (UAI).
URL PDF
Y. Yu (2016). Online Learning and Optimization. Encyclopedia of Algorithms.
URL PDF
Y. Yu, E. Xing (2015). Exact Algorithms for Isotonic Regression and Related. Journal of Physics: Conference Series.
URL PDF
X. Chang, Y. Yu, Y. Yang, A. Hauptmann (2015). Searching Persuasively: Joint Event Detection and Evidence Recounting with Limited Supervision. ACM Conference on Multimedia (MM).
URL PDF
E. Xing, Q. Ho, W. Dai, J. Kim, J. Wei, S. Lee, X. Zheng, P. Xie, A. Kumar, Y. Yu (2015). Petuum: A New Platform for Distributed Machine Learning on Big Data. IEEE Transactions on Big Data.
URL PDF
X. Zheng, Y. Yu, E. Xing (2015). Linear Time Samplers for Supervised Topic Models using Compositional Proposals. ACM Conference on Knowledge Discovery and Data Mining (KDD).
URL PDF Code
X. Chang, Y. Yang, A. Hauptmann, E. Xing, Y. Yu (2015). Semantic Concept Discovery for Large-Scale Zero-Shot Event Detection. International Joint Conference on Artificial Intelligence (IJCAI).
URL PDF
X. Chang, Y. Yang, E. Xing, Y. Yu (2015). Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM. International Conference on Machine Learning (ICML).
URL PDF
Y. Yu, X. Zheng, M. Marchetti-Bowick, E. Xing (2015). Minimizing Nonconvex Non-Separable Functions. International Conference on Artificial Intelligence and Statistics (AISTATS).
URL PDF
A. Yu, W. Ma, Y. Yu, J. Carbonell, S. Sra (2014). Efficient Structured Matrix Rank Minimization. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
X. Zhang, Y. Yu, D. Schuurmans (2013). Polar Operators for Structured Sparse Estimation. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu (2013). Better Approximation and Faster Algorithm Using the Proximal Average. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu (2013). On Decomposing the Proximal Map. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu, H. Cheng, D. Schuurmans, C. Szepesvári (2013). Characterizing the Representer Theorem. International Conference on Machine Learning (ICML).
URL PDF
M. White, Y. Yu, X. Zhang, D. Schuurmans (2012). Convex Multi-view Subspace Learning. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
X. Zhang, Y. Yu, D. Schuurmans (2012). Accelerated Training for Matrix-Norm Regularization: A Boosting Approach. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu, Ö. Aslan, D. Schuurmans (2012). A Polynomial-time Form of Robust Regression. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu, J. Neufeld, R. Kiros, X. Zhang, D. Schuurmans (2012). Regularizers versus Losses for Nonlinear Dimensionality Reduction. International Conference on Machine Learning (ICML).
URL PDF
Y. Yu, C. Szepesvári (2012). Analysis of Kernel Mean Matching under Covariate Shift. International Conference on Machine Learning (ICML).
URL PDF
X. Zhang, Y. Yu, M. White, R. Huang, D. Schuurmans (2011). Convex Sparse Coding, Subspace Learning, and Semi-Supervised Extensions. Association for the Advancement of Artificial Intelligence (AAAI).
URL PDF
Y. Yu, J. Jiang, L. Zhang (2011). Distance Metric Learning by Minimal Distance Maximization. Pattern Recognition.
URL PDF
Y. Yu, D. Schuurmans (2011). Rank/Norm Regularization with Closed-Form Solutions: Application to Subspace Clustering. Conference on Uncertainty in Artificial Intelligence (UAI).
URL PDF
Y. Yu, M. Yang, L. Xu, M. White, D. Schuurmans (2010). Relaxed Clipping: A Global Training Method for Robust Regression and Classification. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu, Y. Zhang, C. Szepesvári (2009). Online TD(1) Meets Offline Monte Carlo. Multidisciplinary Symposium on Reinforcement Learning.
Y. Yu, Y. Li, D. Schuurmans, C. Szepesvári (2009). A General Projection Property for Distribution Families. Advances in Neural Information Processing Systems (NeurIPS).
URL PDF
Y. Yu, C. Szepesvári, Y. Li, D. Schuurmans (2009). A Conditional Value-at-Risk Approach for Uncertain Markov Decision Processes. Multidisciplinary Symposium on Reinforcement Learning.