2025
Yuchen Liang, Yingbin Liang, Lifeng Lai, Ness Shroff. “Discrete diffusion models: Novel analysis and new sampler guarantees”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2025. [arXiv]
Yuchen Liang, Yingbin Liang, Lifeng Lai, Ness Shroff. “Absorb and converge: Provable convergence guarantee for absorbing discrete diffusion models”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2025. [arXiv]
Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi. “Multi-head transformers provably learn symbolic multi-step reasoning via gradient descent”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2025. [arXiv]
Ruiquan Huang, Yingbin Liang, Jing Yang. “Robust offline reinforcement learning for non-Markovian decision processes”, IEEE Transactions on Information Theory, vol. 71, no. 9, 7208 – 7228, 2025. [arXiv]
Ruiquan Huang, Yingbin Liang, Jing Yang. “How transformers learn regular language recognition: A theoretical study on training dynamics and implicit bias”, Proc. International Conference on Machine Learning (ICML), 2025. [arXiv]
Junze Deng, Qinhang Wu, Peizhong Ju, Sen Lin, Yingbin Liang, Ness Shroff. “Unlocking the power of rehearsal in continual learning: A theoretical perspective”, Proc. International Conference on Machine Learning (ICML), 2025. [arXiv]
Ziwei Guan, Daouda Sow, Sen Lin, Yingbin Liang. “AdaProx: A novel method for bilevel optimization under pessimistic framework”, Conference on Parsimony and Learning (CPAL), 2025. [Conference Proceedings]
Junjie Yang, Jinze Zhao, Peihao Wang, Zhangyang Wang, Yingbin Liang. “Meta ControlNet: Enhancing task adaptation via meta learning”, Conference on Parsimony and Learning (CPAL), 2025. [arXiv]
Daouda Sow, Herbert Woisetschläger, Saikiran Bulusu, Shiqiang Wang, Hans Arno Jacobsen, Yingbin Liang. "Dynamic loss-based sample reweighting for improved large language model pretraining", International Conference on Learning Representations (ICLR), 2025.
Yu Huang, Zixin Wen, Yuejie Chi, Yingbin Liang. "A theoretical analysis of self-supervised learning for vision transformers", International Conference on Learning Representations (ICLR), 2025. [arXiv]
Yuchen Liang, Peizhong Ju, Yingbin Liang, Ness Shroff. "Theory on score-mismatched diffusion models and zero-shot conditional samplers", International Conference on Learning Representations (ICLR), 2025. [arXiv]
Yuchen Liang, Peizhong Ju, Yingbin Liang, Ness Shroff. "Broadening target distributions for accelerated diffusion models via a novel analysis approach", International Conference on Learning Representations (ICLR), 2025. [arXiv]
Hongbo Li, Sen Lin, Lingjie Duan, Yingbin Liang, Ness B. Shroff. "Theory on mixture-of-experts in continual learning", International Conference on Learning Representations (ICLR), 2025. [arXiv]
Hongru Yang, Zhangyang Wang, Jason D. Lee, Yingbin Liang. "Transformers provably learn two-mixture of linear classification via gradient flow", International Conference on Learning Representations (ICLR), 2025.
Zhen Qin, Zhuqing Liu, Songtao Lu, Yingbin Liang, Jia Liu. "DUET: Decentralized bilevel optimization without lower-level strong convexity", International Conference on Learning Representations (ICLR), 2025.
2024
Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi. "In-context learning with representations: Contextual generalization of trained transformers", Proc. Advances in Neural Information Processing Systems (NeurIPS), 2024. [arXiv]
Ruiquan Huang, Yingbin Liang, Jing Yang. “Non-asymptotic convergence of training transformers for next-token prediction”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2024. [arXiv]
Hongru Yang, Bhavya Kailkhura, Zhangyang Wang, Yingbin Liang. “Training dynamics of transformers to recognize word co-occurrence via gradient flow analysis”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2024.
Hongru Yang, Yingbin Liang, Xiaojie Guo, Lingfei Wu, and Zhangyang Wang. “Pruning before training may improve generalization, provably.”, Journal of Machine Learning Research (JMLR), accepted 2024. [arXiv]
Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Yingbin Liang, and Zhangyang Wang. “Neural networks with sparse activation induced by large bias: Tighter analysis with bias-generalized NTK”, Journal of Machine Learning Research (JMLR), accepted 2024. [arXiv]
Peizhong Ju, Haibo Yang, Jia Liu, Yingbin Liang, Ness Shroff. “Can we theoretically quantify the impacts of local updates on the generalization performance of federated learning?”, International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc), 2024.
Ming Shi, Yingbin Liang, Ness Shroff. “Designing Near-Optimal Partially Observable Reinforcement Learning,” MILCOM 2024.
Yu Huang, Yuan Cheng, Yingbin Liang. "In-context convergence of transformers", Proc. International Conference on Machine Learning (ICML), 2024. [arXiv]
Songtao Feng, Ming Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang. “Improving sample efficiency of model-free algorithms for zero-sum Markov games”, Proc. International Conference on Machine Learning (ICML), 2024. [arXiv]
Tengyu Xu, Yue Wang, Shaofeng Zou, Yingbin Liang. “Provably efficient offline reinforcement learning with trajectory-wise reward”, IEEE Transactions on Information Theory, accepted 2024. [arXiv]
Songtao Feng, Min Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang. “Towards General Function Approximation in Nonstationary Reinforcement Learning”, IEEE Journal on Selected Areas in Information Theory (JSAIT), vol. 5, 190 – 206, 2024.
Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan. “Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process” Operations Research Letters (ORL), vol. 54, May 2024. [arXiv]
Junze Deng, Yuan Cheng, Shaofeng Zou, Yingbin Liang. “Sample Complexity Characterization for Linear Contextual MDPs”, Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [arXiv]
Ruiquan Huang, Yuan Cheng, Jing Yang, Vincent Tan, Yingbin Liang. "Provable benefits of multi-task RL under non-Markovian decision making processes", International Conference on Learning Representations (ICLR), 2024. [arXiv]
Ruiquan Huang, Yingbin Liang, Jing Yang. "Provably eafficient UCB-type algorithms for learning predictive state representations", International Conference on Learning Representations (ICLR), 2024. [arXiv]
Daouda Sow, Sen Lin, Zhangyang Wang, Yingbin Liang. "Doubly robust instance-reweighted adversarial training", International Conference on Learning Representations (ICLR), 2024. [arXiv]
Ziwei Guan, Yi Zhou, Yingbin Liang. “On the hardness of online nonconvex optimization with single oracle feedback”, International Conference on Learning Representations (ICLR), 2024.
Daouda Sow, Sen Lin, Yingbin Liang, Junshan Zhang. “Algorithm design for online meta-learning with task boundary detection”, Proc. Conference on Parsimony and Learning (CPAL), 2024. [arXiv]
Sen Lin, Daouda Sow, Kaiyi Ji, Yingbin Liang, Ness Shroff. “Non-convex bilevel optimization with time-varying objective functions”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2023. [arXiv]
Yuan Cheng, Jing Yang, Yingbin Liang. “Provably efficient algorithm for nonstationary low-rank MDPs”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2023. [arXiv]
Ziwei Guan, Yi Zhou, Yingbin Liang. “Online nonconvex optimization with limited instantaneous oracle feedback” Proc. Annual Conference on Learning Theory (COLT), 2023. [link]
Kaiyi Ji, Yingbin Liang. "Lower bounds and accelerated algorithms for bilevel optimization", Journal of Machine Learning Research (JMLR), vol. 24, no. 22, 1-56, 2023. [arXiv]
Yu Huang, Yuan Cheng, Yingbin Liang, Longbo Huang. “Online min-max problems with non-convexity and non-stationarity”, Transactions on Machine Learning Research (TMLR), 2023.
Ming Shi, Yingbin Liang, Ness Shroff. “A near-optimal algorithm for safe reinforcement learning under instantaneous hard constraints”, Proc. International Conference on Machine Learning (ICML), 2023. [arXiv]
Songtao Feng, Ming Yin, Ruiquan Huang, Yu-Xiang Wang, Jing Yang, Yingbin Liang. “Non-stationary reinforcement learning under general function approximation”, Proc. International Conference on Machine Learning (ICML), 2023.
Sen Lin, Peizhong Ju, Yingbin Liang, Ness Shroff. “Theory on forgetting and generalization of continual learning”, Proc. International Conference on Machine Learning (ICML), 2023. [arXiv]
Ziyi Chen, Yi Zhou, Yingbin Liang, Zhaosong Lu, “Generalized-smooth nonconvex optimization is as efficient as smooth nonconvex optimization”, Proc. International Conference on Machine Learning (ICML), 2023. [arXiv]
Ruiquan Huang, Jing Yang, Yingbin Liang. "Safe exploration incurs nearly no additional sample complexity for reward-free RL", International Conference on Learning Representations (ICLR), 2023. [arXiv]
Ming Shi, Yingbin Liang, Ness Shroff. “Near-optimal adversarial reinforcement learning with switching costs”, International Conference on Learning Representations (ICLR), 2023. [arXiv] Spotlight
Yuan Cheng, Ruiquan Huang, Yingbin Liang, Jing Yang. "Improved sample complexity for reward-free reinforcement learning under low-rank MDPs", International Conference on Learning Representations (ICLR), 2023.
Junjie Yang, Xuxi Chen, Tianlong Chen, Zhangyang Wang, Yingbin Liang. “M-L2O: Towards generalizable learning-to-optimize by test-time fast self-adaptation”, International Conference on Learning Representations (ICLR), 2023. [arXiv]
Peizhong Ju, Yingbin Liang, Ness Shroff. “Theoretical characterization of the generalization performance of overfitted meta-learning”, International Conference on Learning Representations (ICLR), 2023. [arXiv]
Junjie Yang, Tianlong Chen, Mingkang Zhu, Fengxiang He, Dacheng Tao, Yingbin Liang, and Zhangyang Wang. "Learning to generalize provably in learning to optimize", International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. [arXiv]
Xuyang Chen, Jingliang Duan, Yingbin Liang, Lin Zhao. “Global convergence of two-timescale actor-critic for solving linear quadratic regulator”, Proc. AAAI Conference on Artificial Intelligence (AAAI), 2023.
Yu Huang, Yingbin Liang, Longbo Huang. "Provable generalization of overparameterized meta-learning trained with SGD", Advances in Neural Information Processing Systems (NeurIPS), 2022. Spotlight [arXiv]
Yuan Cheng, Songtao Feng, Jing Yang, Hong Zhang, Yingbin Liang. "Provable benefit of multitask representation learning in reinforcement learning", Advances in Neural Information Processing Systems (NeurIPS), 2022. Spotlight [arXiv]
Kaiyi Ji, Mingrui Liu, Yingbin Liang, Lei Ying. "Will bilevel optimizers benefit from loops", Advances in Neural Information Processing Systems (NeurIPS), 2022. Spotlight [arXiv]
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang. "A unified off-policy evaluation approach for general value function", Advances in Neural Information Processing Systems (NeurIPS), 2022. [arXiv]
Daouda Sow, Kaiyi Ji, Yingbin Liang. "On the convergence theory for Hessian-free bilevel algorithms", Advances in Neural Information Processing Systems (NeurIPS), 2022. [arXiv]
Shaocong Ma, Ziyi Chen, Yi Zhou, Kaiyi Ji, Yingbin Liang. “Data sampling affects the complexity of online SGD over dependent data”, Proc. 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022. [arXiv]
Huaqing Xiong, Tengyu Xu, Lin Zhao, Yingbin Liang, Wei Zhang. “Deterministic policy gradient: convergence analysis”, Proc. 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022.
Ziwei Guan, Tengyu Xu, Yingbin Liang. "PER-ETD: A polynomially efficient emphatic temporal difference learning method", International Conference on Learning Representations (ICLR), 2022. [arXiv]
S. Lin, J. Wan, T. Xu, Y. Liang, and J. Zhang, “Model-based offline meta-reinforcement learning with regularization”, International Conference on Learning Representations (ICLR), 2022. [arXiv]
Yi Zhou, Yingbin Liang, Huishuai Zhang. “Understanding generalization error of SGD in nonconvex optimization”, Machine Learning, vol. 111, 345-375, 2022. [arXiv]
B. Dai, C. Li, Y. Liang, Z. Ma, S. Shamai, “Self-Secure Capacity-Achieving Feedback Schemes of Gaussian Multiple-Access Wiretap Channels with Degraded Message Sets”, IEEE Transactions on Information Forensics & Security, vol. 17, 1583-1596, 2022. [link to ieeexplore]
Junjie Yang, Kaiyi Ji, Yingbin Liang. “Provably faster algorithms for bilevel optimization”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2021. Spotlight [arXiv]
Lin Zhao, Huaqing Xiong, Yingbin Liang. “Faster non-asymptotic convergence for double Q-learning.” Advances in Neural Information Processing Systems (NeurIPS), 2021. [link to paper]
Qunwei Li, Bhavya Kailkhura, Rushil Anirudh, Jize Zhang, Yi Zhou, Yingbin Liang, T. Yong-Jin Han, and Pramod K. Varshney, “MR-GAN: manifold regularized generative adversarial networks for scientific data,” accepted in SIAM Journal on Mathematics of Data Science (SIMODS), 2021.
Kaiyi Ji, Yi Zhou, Yingbin Liang. “Understanding estimation and generalization error of generative adversarial networks”, IEEE Transactions on Information Theory, vol. 67, no. 5, 3114-3129, May 2021. [ieeexplore]
K. Ji, J. Yang, Y. Liang. “Theoretical convergence of multi-step model-agnostic meta-learning”, Journal of Machine Learning Research (JMLR), 2021. [arXiv]
Tengyu Xu, Yingbin Liang, Guanghui. Lan. “CRPO: A new approach for safe reinforcement learning with convergence guarantee”, Proc. International Conference on Machine Learning (ICML), 2021. [arXiv]
Kaiyi Ji, Junjie Yang, Yingbin Liang. “Bilevel optimization: Convergence analysis and enhanced design”, Proc. International Conference on Machine Learning (ICML), 2021. [arXiv]
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang. “Doubly robust off-policy actor-critic: Convergence and optimality”, Proc. International Conference on Machine Learning (ICML), 2021. [arXiv]
Bowen Weng, Huaqing Xiong, Lin Zhao, Yingbin Liang, Wei Zhang. “Finite-time theory for momentum Q-learning”, Proc. Conference on Uncertainty in Artificial Intelligence (UAI), 2021. [arXiv]
H. Qiong, T. Xu, Y. Liang, W. Zhang. “Non-asymptotic convergence analysis of Adam-type reinforcement learning algorithms under Markovian sampling”, Proc. AAAI Conference on Artificial Intelligence (AAAI), 2021. [arXiv]
Z. Chen, Y. Zhou, T. Xu, Y. Liang. “Proximal gradient descent-ascent: Variable convergence under KL geometry”, Proc. Sixth International Conference on Learning Representations (ICLR), 2021. {arXiv]
Ziwei Guan, Tengyu Xu, Yingbin Liang. “When will generative adversarial imitation learning algorithms attain global convergence”, Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. {arXiv]
Tengyu Xu, Yingbin Liang. “Sample complexity bounds for two timescale value-based reinforcement learning algorithms”, Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. {arXiv]
Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor. “Convergence of meta-learning with task-specific adaptation over partial parameters”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2020. [arXiv]
T. Xu, Z. Wang, Y. Liang. “Improving sample complexity bounds for (natural) actor-critic Algorithms”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2020. [arXiv]
Huaqing Qiong, Lin Zhao, Yingbin Liang, Wei Zhang. "Finite-Time Analysis for Double Q-learning", Proc. Advances in Neural Information Processing Systems (NeurIPS), 2020. Spotlight [arXiv]
T. Xu, Z. Wang, Y. Liang. “Non-asymptotic convergence analysis of two time-scale (natural) actor-critic algorithms”, Technical report, 2020. [arXiv]
Z. Wang, P. Ji, Y. Liang. “Spectral algorithms for community detection in directed networks”, Journal of Machine Learning Research (JMLR), vol. 21, 1-45, 2020. [arXiv]
K. Ji, Z. Wang, B. Weng, Y. Zhou, W. Zhang, Y. Liang. “History-gradient aided batch size adaptation for variancereduced algorithms” Proc. International Conference on Machine Learning (ICML), 2020. [arXiv]
Tengyu Xu, Yi Zhou, Kaiyi Ji, Yingbin Liang. “When will gradient methods converge to max-margin classifier under ReLU models?” Stat, Special Issue of Deep Learning from Statistical Perspective, December 2020.
T. Xu, Z. Wang, Y. Zhou, Y. Liang. “Reanalysis of variance reduced temporal difference learning”, Proc. International Conference on Learning Representations (ICLR), 2020. [arXiv]
Z. Guan, K. Ji, D. J. Bucci Jr, T. Hu, J. Palombo, M. Liston, Y. Liang “Median-based robust stochastic bandit algorithms under probabilistic unbounded adversarial attack”, Proc. AAAI Conference on Artificial Intelligence (AAAI), 2020. [arXiv]
B. Wong, H. Qiong, Y. Liang, W. Zhang. “Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent”, Proc. International Joint Conference on Artificial Intelligence --Pacific Rim International Conference on Artificial Intelligence (IJCAI), 2020. (acceptance ratio: 12.6%) [arXiv]
Y. Zhou, Z. Wang, K. Ji, Y. Liang, V. Tarokh. “A convergent accelerated proximal gradient with restart for nonconvex optimization”, Proc. International Joint Conference on Artificial Intelligence --Pacific Rim International Conference on Artificial Intelligence (IJCAI), 2020. (acceptance ratio: 12.6%) [arXiv]
H. Fu, Y. Chi, Y. Liang. “Guaranteed recovery of one-hidden-layer neural networks via cross entropy” IEEE Transactions on Signal Processing, vol. 68, 3225-3235, 2020.
B. Dai, C. Li, Y. Liang, Z. Ma, S. Shamai (Shitz). “Impact of action-dependent state and channel feedback on Gaussian wiretap channels", IEEE Transactions on Information Theory, vol. 66, no. 6, 3435-3455, 2020.
B. Dai, C. Li, Y. Liang, Z. Ma, S. Shamai, “On the capacity of Gaussian multiple-access wiretap channels with feedback”, Proc. International Symposium on Information Theory and Its Applications (ISITA), 2020.
B. Dai, C. Li, Y. Liang, Z. Ma, S. Shamai, “Feedback capacity of Gaussian multiple-access wiretap channel with degraded message sets”, Proc. IEEE Information Theory Workshop (ITW), 2020.
Z. Wang, K. Ji, Y. Zhou, Y. Liang, V. Tarokh. “SpiderBoost and momentum: Faster variance reduction algorithms”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2019.
T. Xu, S. Zou, Y. Liang. “Two time-scale off-policy TD learning: Non-asymptotic analysis over Markovian samples”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2019.
S. Zou, T. Xu, Y. Liang. “Finite-sample analysis for SARSA with linear function approximation”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2019.
Z. Wang, Y. Zhou, Y. Liang, G. Lan. “Cubic regularization with momentum for nonconvex optimization”, Proc. Conference on Uncertainty in Artificial Intelligence (UAI), 2019.
K. Ji, Z. Wang, Y. Zhou, Y. Liang. “Improved zeroth-order variance reduced algorithms and analysis for nonconvex optimization”, Proc. International Conference on Machine Learning (ICML), 2019.
Y. Zhou, J. Yang, H. Zhang, Y. Liang, V. Tarokh. “SGD converges to global minimum in deep learning via star-convex path”, Proc. International Conference on Learning Representations (ICLR), 2019.
Z. Wang, Y. Zhou, Y. Liang, G. Lan “Stochastic variance-reduced cubic regularization for nonconvex optimization”, Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.
C. Li, Y. Liang, H. Vincent Poor, S. Shamai (Shitz). “Secrecy capacity of colored Gaussian noise channels with feedback”, IEEE Transactions on Information Theory, vol. 65, no. 9, 5771-5782, 2019.
Y. Li, Y. Chi, H. Zhang, Y. Liang. “Nonconvex low-rank matrix recovery with arbitrary outliers via median-truncated gradient descent”, Information and Inference, 2019.
Y. Zhou, Y. Liang, L. Shen. “A simple convergence analysis of Bregman proximal gradient algorithm”, Computational Optimization and Applications, vol. 73, no. 3, 903-912, July 2019.
W. Zhe. Y. Zhou, Y. Liang, G. Lan. “A note on inexact gradient and Hessian conditions for cubic regularized Newton’s method”, Operations Research Letters, vol. 47, no. 2, 146-149, 2019.
T. Wang, Q. Li, D. J. Bucci, Y. Liang, B. Chen, P. K. Varshney. “K-mediods clustering of data sequences with composite distributions”, IEEE Transactions on Signal Processing, vol. 67, no. 8, 2093-2106, April 2019.
Y. Sun, R. Duan, Y. Liang, S. Shamai. “State-dependent interference channel with correlated states”, IEEE Transactions on Information Theory, vol. 65, no. 7, 4518-4531, July 2019.
M. Dikshtein, R. Duan, Y. Liang and S. Shamai (Shitz). “MIMO Gaussian state-dependent channels with a state-cognitive helper”, Entropy, March 2019.
H. Fu, Y. Chi, Y. Liang. “Local geometry of cross entropy loss in learning one-hidden-layer neural networks”, Proc. IEEE International Symposium on Information Theory (ISIT), 2019.
B. Dai, C. Li, Y. Liang, Z. Ma, S. Shamai, “The dirty paper wiretap feedback channel with or without action on the state”, Proc. IEEE International Symposium on Information Theory (ISIT), 2019.
K. Ji, Y. Liang. “Minimax estimation of neural net distance”, Proc. Advances in Neural Information Processing Systems (NeurIPS), 2018.
Y. Zhou, Z. Wang, Y. Liang. “Convergence of cubic regularization for nonconvex optimization under KL property.” Proc. Advances in Neural Information Processing Systems (NeurIPS), 2018. Spotlight
M. Dikshtein, R. Duan, Y. Liang and S. Shamai (Shitz), “Parallel Gaussian channels corrupted by independent states with a state-cognitive helper,” Proc. International Conference on the Science of Electrical Engineering (ICSEE), 2018.
Y. Zhou, Y. Liang. “Critical points of linear neural networks: Analytical forms and landscape properties”, Proc. Sixth International Conference on Learning Representations (ICLR), 2018.
Y. Zhou, Y. Liang, Y. Yu, W. Dai, E. Xing. “Distributed proximal gradient algorithm for partially asynchronous computer cluster”, Journal of Machine Learning Research, (JMLR), vol. 19, no. 1, 733-764, January 2018.
Y. Liu, Y. Liang, S. Cui. “Data-driven nonparametric hypothesis testing”, Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.
T. Wang, D. J. Bucci, Y. Liang, B. Chen, P. K. Varshney. “Exponentially consistent k-means clustering algorithm based on Kolmogrov-Smirnov test”, Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.
H. Zhang, Y. Chi, Y. Liang. “Median truncated nonconvex approach for phase retrieval with outliers”, IEEE Transactions on Information Theory, vol. 64, no. 11, 7287-7310, November 2018.
Q. Li, T. Wang, D. J. Bucci, Y. Liang, B. Chen, P. K. Varshney. “Nonparametric composite hypothesis testing in an asymptotic regime”, Journal of Selected Topics in Signal Processing, vol. 12, no. 5, 1005-1014, October 2018.
Y. Bu, S. Zou, Y. Liang, V. Veeravalli. “Estimation of KL divergence: Optimal minimax rate”, IEEE Transactions on Information Theory, vol. 64, no. 4, 2648-2674, April 2018.
C. Li, Y. Liang, H. V. Poor, S. Shamai (Shitz) “A coding theorem for colored Gaussian wiretap channels with feedback”, Proc. IEEE International Symposium on Information Theory (ISIT), 2018.
T. Wang, D. J. Bucci, Y. Liang, B. Chen, P. K. Varshney. “Clustering under composite generative models”, Proc. 52nd Annual Conference on Information Systems and Sciences (CISS), 2018.
M. Dikshtein, R. Duan, Y. Liang and S. Shamai (Shitz). “State-dependent parallel Gaussian channels with a state-cognitive helper”, Proc. International Zurich Seminar on Information and Communication (IZS), 2018.
Y. Liu, Y. Liang, S. Cui. “Data-driven nonparametric existence and association problems”, IEEE Transactions on Signal Processing, vol. 66, no. 24, 6377-6389, December 2018.
W. Yang, Y. Liang, H. Vincent Poor, S. Shamai (Shitz) “State-dependent Gaussian multiple access channels: New outer bounds and capacity results”, IEEE Transactions on Information Theory, vol. 64, no. 12, 7866-7882, December 2018.
S. Zou, Y. Liang, L. Lai, H. V. Poor and S. Shamai (Shitz). “Degraded broadcast channel with secrecy outside a bounded range”, IEEE Transactions on Information Theory, vol. 64, no. 3, 2104-2120, March 2018.
H. Zhang, Y. Zhou, Y. Liang, Y. Chi. “A nonconvex approach for phase retrieval: Reshaped Wirtinger flow and incremental algorithms”, Journal of Machine Learning Research (JMLR), 18(141):1−35, 2017.
Q. Li, Y. Zhou, Y. Liang, P. Varshney. “Convergence analysis of proximal gradient with momentum for nonconvex optimization”, Proc. International Conference on Machine Learning (ICML), 2017.
Y. Li, Y. Chi, H. Zhang, Y. Liang. “Non-convex low-rank matrix recovery from corrupted random linear measurements” 12th International Conference of Sampling Theory and Applications (SampTA), Tallinn, June 2017.
S. Zou, Y. Liang, S. Shamai. “Gaussian fading channel with secrecy outside a bounded range”, Proc. IEEE Conference on Communications and Network Security (CNS), (invited paper), 2017.
Ain-ul-Aisha, L. Lai, Y. Liang and S. Shamai (Shitz), “On the sum-rate capacity of Poisson multi-antenna multiple access channels”, IEEE Transactions on Information Theory, vol. 63, no. 10, 6457–6473, October 2017.
S. Zou, Y. Liang, H. V. Poor. “Nonparametric detection of geometric structures over networks”, IEEE Transactions on Signal Processing, vol. 65, no. 19, 5034-5046, October 2017.
Ain-ul-Aisha, L. Lai, Y. Liang and S. Shamai (Shitz), “Sum-rate capacity of Poisson MIMO multiple-access channels,” IEEE Transactions on Communications, vol. 65, no. 11, 4765-4776, August 2017.
H. Zhang, Y. Liang, L. Lai, S. Shamai (Shitz). “Multi-key generation over a cellular model with a helper”, IEEE Transactions on Information Theory, vol. 63, no. 6, 3804-3822, June 2017.
Y. Sun, R. Duan, Y. Liang, S. Shamai. “State-dependent Z-interference channel with correlated states”, Proc. IEEE International Symposium on Information Theory (ISIT), 2017.
W. Yang, Y. Liang, H. V. Poor, S. Shamai. “Outer bounds for multiple access channels with state known at one encoder”, Proc. IEEE International Symposium on Information Theory (ISIT), 2017.
C. Li, Y. Liang. “Secrecy capacity of the first-order autoregressive moving average Gaussian channel with feedback”, Proc. IEEE International Symposium on Information Theory (ISIT), 2017.
Y. Zhou, Y. Liang. “Demixing sparse signals via convex optimization”, Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.
S. Zou, Y. Liang, H. V. Poor, X. Shi. “Nonparametric detection of anomalous data streams”, IEEE Transactions on Signal Processing, vol. 65, no. 21, 5785-5797, November 2017.
H. Zhang, Y. Liang. “Reshaped Wirtinger flow for solving quadratic systems of equations”, Proc. Advances in Neural Information Processing Systems (NIPS), December 2016.
Y. Sun, R. Duan, Y. Liang, A. Khisti, S. Shamai. “Capacity characterization for state-dependent Gaussian channel with a helper”, IEEE Transactions on Information Theory, vol. 62, no. 12, 7123-7134, December 2016.
R. Duan, Y. Liang, S. Shamai. “State-dependent Gaussian interference channels: Can state be fully cancelled?”, IEEE Transactions on Information Theory, vol. 62, no. 4, 1957 – 1970, April 2016.
W. Wang, Y. Liang, E. P. Xing, L. Shen. “Nonparametric decentralized detection and sparse sensor selection via weighted kernel” IEEE Transactions on Signal Processing, vol. 64, no. 2, 306-321, January 2016.
Ain-ul-Aisha, L. Lai, Y. Liang and S. Shamai. “On the sum-rate capacity of non-symmetric Poisson multiple access channel”, IEEE International Symposium on Information Theory (ISIT), 2016.
Y. Bu, S. Zou, Y. Liang, V. Veeravalli. “Estimation of KL divergence between large-alphabet distributions”, Proc. IEEE International Symposium on Information Theory (ISIT), 2016.
Y. Sun, R. Duan, Y. Liang, A. Khisti, S. Shamai. “Helper-assisted state cancelation for multiple access channels”, Proc. IEEE International Symposium on Information Theory (ISIT), 2016.
S. Zou, Y. Liang, L. Lai, H. V. Poor, S. Shamai. “K-user degraded broadcast channel with secrecy outside a bounded range”, Proc. IEEE Information Theory Workshop (ITW), September 2016.
Ain-ul-Aisha, L. Lai, Y. Liang and S. Shamai. “On the sum-rate capacity of Poisson MISO multiple access channels”, IEEE International Conference on Communication Systems (ICCS), 2016.
W. Wang, Y. Liang, H. V. Poor. “Nonparametric composite outlier detection”, Proc. 50th Asilomar Conference on Signals, Systems and Computers, November 2016.
Y. Zhou, H. Zhang, Y. Liang. “Geometrical properties and accelerated gradient solvers of non-convex phase retrieval”, Proc. 54th Annual Allerton Conference on Communication, Control, and Computing, October 2016.
Y. Zhou, H. Zhang, Y. Liang. “On compressive orthonormal sensing”, Proc. 54th Annual Allerton Conference on Communication, Control, and Computing, October 2016.
H. Zhang, Y. Chi, Y. Liang. “Provable non-convex phase retrieval with outliers: Median truncated Wirtinger flow”, Proc. International Conference on Machine Learning (ICML), June 2016.
S. Zou, Y. Liang, H. V. Poor. “Nonparametric detection of an anomalous disk over a two-dimensional lattice network” Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016.
Y. Bu, S. Zou, Y. Liang, V. V. Veeravalli. “Universal outlying sequence detection for continuous observations” Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016.
Y. Zhou, Y. Yu, Y. Liang, E. P. Xing. “On convergence of model parallel proximal gradient algorithm for stale synchronous parallel system”, Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
H. Zhang, Y. Zhou, Y. Liang. “Analysis of robust PCA via local incoherence”, Proc. Advances in Neural Information Processing Systems (NIPS), 2015.
R. Duan, Y. Liang, A. Khisti, S. Shamai. “Parallel Gaussian networks with a common state-cognitive helper”, IEEE Transactions on Information Theory, vol. 61, no. 12, 6680 – 6699, December 2015.
S. Zou, Y. Liang, L. Lai, H. V. Poor, S. Shamai. “Broadcast networks with layered decoding and layered secrecy: Theory and applications”, Proc. IEEE, vol. 103, no. 10, 1841-1856, September 2015.
S. Zou, Y. Liang, L. Lai, S. Shamai (Shitz) “An information theoretic approach to secret sharing”, IEEE Transactions on Information Theory, vol. 61, no. 6, pp. 3121-3136, June 2015.
W. Wang, Y. Liang, E. P. Xing. “Collective support recovery for multi-design multi-response linear regression”, IEEE Transactions on Information Theory, vol. 61, no. 1, pp.513-534, Jan. 2015.
L. Lai, Y. Liang, S. Shamai (Shitz). “On the capacity bounds for Poisson interference channels”, IEEE Transactions on Information Theory, vol. 61, no. 1, pp.223-238, Jan. 2015.
R. Duan, Y. Liang. “Bounds and capacity theorems for cognitive interference channels with state”, IEEE Transactions on Information Theory, vol. 61, no. 1, pp.280-304, Jan. 2015.
A. He, B. Hall, J. Wen, Y. Liang, X. Shi. “Sequential parallel LASSO models for eQTL analysis”, Proc. ACM Conference on Bioinformatics, Computational Biology and Health Informatics, 2015.
S. Zou, Y. Liang, L. Lai, S. Shamai. “Rate splitting and sharing for degraded broadcast channel with secrecy outside of a bounded range”, Proc. IEEE International Symposium on Information Theory (ISIT), 2015.
R. Duan, Y. Liang, S. Shamai. “State-Dependent Gaussian Z-Interference Channel: Capacity Results”, Proc. IEEE International Symposium on Information Theory (ISIT), 2015.
H. Zhang, Y. Liang, L. Lai, S. Shamai. “Two key generation for a cellular model with a helper”, Proc. IEEE International Symposium on Information Theory (ISIT), 2015.
H. Zhang, Y. Liang L. Lai. “Secret key capacity: talk or keep silent?”, Proc. IEEE International Symposium on Information Theory (ISIT), 2015.
S. Zou, Y. Liang, L. Lai, S. Shamai. “Degraded Broadcast Channel: Secrecy Outside of a Bounded Range”, Proc. IEEE Information Theory Workshop (ITW), April 2015.
Ain-ul-Aisha, L. Lai and Y. Liang. “Optimal power allocation for Poisson channels with time-varying background light”, IEEE Transactions on Communications, 63, no. 11, 4327-4338, Nov. 2015.