-
Assistant Professor, Elect & Computer Engineering
-
Adjunct Assistant Professor, Elect & Computer Engineering
Publications
- C. Chen & J. Zhang, J. Ding, and Y. Zhou (2023). Assisted unsupervised domain adaptation. IEEE International Symposium on Information Theory (ISIT).
Published, 06/01/2023.
- Z. Chen & Y. Zhou, Y. Liang, and Z. Lu (2023). Generalized-smooth nonconvex optimization is as efficient as smooth nonconvex optimization. International Conference on Machine Learning (ICML).
Published, 05/01/2023.
- J. Cho & M. Liu, Yi Zhou, and R.-R. Che (2023). Multi-agent recurrent deterministic policy gradient with inter-agent communication (mardpg-iac). Asilomar Conference on Signals, Systems, and Computers.
Published, 04/01/2023.
- Z. Guan & Y. Zhou, and Y. Liang (2023). Online nonconvex optimization with limited instantaneous oracle feedback. Conference on Learning Theory (COLT).
Published, 03/01/2023.
- Z. Li & Q. Li, Y. Zhou, W. Zhong, G. Zhang, and C. W (2023). Edge-cloud collaborative learning with federated and centralized features. nternational ACM SIGIR Conference on Research and Development in Information Retrieval.
Published, 02/01/2023.
- C. Morchdi & Y. Zhou, J. Ding, and B. Wang (2023). “Exploring gradient oscillation in deep neural network training. Allerton Conference on Communication, Control, and Computing.
Published, 01/01/2023.
- Y. Zhou & J. Ding, and B. Wang (2022). Visualizing and analyzing the topology of neuron activations in deep adversarial training. ICML Workshop on Topology, Algebra, and Geometry in Machine Learning.
Published, 06/01/2022.
- Z. Chen & S. Ma*, and Y. Zhou (2022). Accelerated proximal alternating gradient-descent-ascent for nonconvex minimax machine learning. IEEE International Symposium on Information Theory (ISIT).
Published, 05/01/2022.
- Z. Chen & S. Ma*, and Y. Zhou (2022). Finding correlated equilibrium of constrained markov game: A primal-dual approach. Advances in Neural Information Processing Systems (NeurIPS).
Published, 04/01/2022.
- Z. Chen & S. Ma*, and Y. Zhou (2022). Sample efficient stochastic policy extragradient algorithm for zero-sum markov game. International Conference on Learning Representations (ICLR).
Published, 03/01/2022.
- S. Ma & Z. Chen*, Y. Zhou, K. Ji, and Y. Liang (2022). Data sampling affects the complexity of online sgd over dependent data. Conference on Uncertainty in Artificial Intelligence (UAI).
Published, 02/01/2022.
- Z. Chen & Y. Zhou, R.-R. Chen, and S. Zo (2022). Sample and communication-efficient decentralized actor-critic algorithms with finite-time analysis. International Conference on Machine Learning (ICML).
Published, 02/01/2022.
- Y. Wang & Y. Zhou, A. Velasquez, and S. Zou (2022). Data-driven robust multi-agent reinforcement learning. IEEE International Workshop on Machine Learning for Signal Processing (MLSP).
Published, 01/01/2022.
- C. Chen & B. Kailkhura, R. Goldhahn, and Y. Zhou (2021). Certifiably-robust federated adversarial learning via randomized smoothing. EEE International Conference on Mobile Ad Hoc and Smart Systems (MASS).
Published, 11/02/2021.
- Z. Chen & Y. Zhou, T. Xu, and Y. Liang (2021). Proximal gradient descent-ascent: Variable convergence under kŁ geometry. International Conference on Learning Representations (ICLR).
Published, 11/01/2021.
- J. Cho & M. Liu, Y. Zhou, and R.-R. Che (2021). Communication-free two-stage multi-agent ddpg under partial states and observations. Asilomar Conference on Signals, Systems, and Computers.
Published, 10/01/2021.
- Y. Wang, S. Zou & Y. Zhou (2021). Non-asymptotic analysis for two time-scale TDC with general smooth function approximation. NeurIPS.
Published, 09/01/2021.
- S. Ma & Z. Chen*, Y. Zhou, and S. Zou (2021). Greedy-gq with variance reduction: Finite-time analysis and improved complexity. International Conference on Learning Representations.
Published, 03/31/2021.
- Chris Cannella & Jie Ding, Mohammadreza Soltani, Yi Zhou, Vahid Tarokh (2020). Perception-Distortion Trade-off with Restricted Boltzmann Machines. ICASSP.
Published, 12/01/2020.
- Kaiyi Ji & Zhe Wang, Bowen Weng, Yi Zhou, Wei Zhang, Yingbin Liang (2020). History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms. ICML 2020.
Published, 12/01/2020.
- Yi Zhou & Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh (2020). Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization. IJCAI2020.
Published, 12/01/2020.
- Cat P. Le & Yi Zhou, Jie Ding, Vahid Tarokh (2020). SUPERVISED ENCODING FOR DISCRETE REPRESENTATION LEARNING. ICASSP.
Published, 12/01/2020.
- Tengyu Xu, Zhe Wang, Yi Zhou & Yingbin Liang (2020). Reanalysis of Variance Reduced Temporal Difference Learning. International Conference on Learning Representations (ICLR).
Published, 12/01/2020.
- Cheng Chen & Junjie Yang, Yi Zhou (2020). Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study. IEEE Bigdata 2020.
Published, 12/01/2020.
- Shaocong Ma & Yi Zhou, Shaofeng Zou (2020). Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis. NeurIPS 2020.
Published, 12/01/2020.
- Bhavya Kailkhura & Yi Zhou (2020). A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning. NeurIPS 2020.
Published, 12/01/2020.
- Shaocong Ma & Yi Zhou (2020). Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle. ICML 2020.
Published, 12/01/2020.
- Cheng Chen & Ziyi Chen, Yi Zhou, Bhavya Kailkhura (2020). FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling. IEEE Bigdata 2020.
Published, 12/01/2020.
- Zhe Wang, Yi Zhou, Yingbin Liang & Guanghui Lan (2019). Cubic Regularization with Momentum for Nonconvex Optimization. Uncertainty in AI (UAI).
Published, 12/01/2019.
- Zhe Wang, Yi Zhou & Yingbin Liang (2019). Sample Complexity of Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization. Artificial Intelligence and Statistics (AISTATS).
Published, 12/01/2019.
- Yi Zhou, Junjie Yang, Huishuai Zhang & Yingbin Liang (2019). SGD Converges to Global Minimum in Deep Learning via Star- convex Path. International Conference on Learning Representations (ICLR).
Published, 12/01/2019.
- Wei Dai, Yi Zhou, Nanqing Dong, Hao Zhang & Eric Xing (2019). Toward Understanding the Impact of Staleness in Distributed Machine Learning. International Conference on Learning Representations (ICLR).
Published, 12/01/2019.
- Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang & Vahid Tarokh (2019). SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization. Neural Information Processing Systems (NeurIPS).
Published, 12/01/2019.
- Yi Zhou, Wang Zhe & Yingbin Liang (2019). Convergence of Cubic Regularization for Nonconvex Optimization under KŁ Property. Neural Information Processing Systems (NeurIPS),.
Published, 12/01/2019.
- J. Regatti, G. Tendolkar, Y. Zhou, A. Gupta & Y. Liang (2019). Distributed SGD Generalizes Well Under Asynchrony. Annual Allerton Conference.
Published, 12/01/2019.
- Y. Feng, Y. Zhou & V. Tarokh (2019). Recurrent Neural Network-Assisted Adaptive Sampling for Approximate Computing. IEEE Bigdata conference.
Published, 12/01/2019.
- Y. Zhou, Y. Feng, V. Tarokh, V. Gintautas, J. Mcclelland & D. Garagic (2019). Multi-level Mean-shift Clustering for Single-channel Radio Frequency Signal Separation. Machine Learning for Signal Processing (MLSP).
Published, 12/01/2019.
- Zhe Wang, Yi Zhou, Yingbin Liang & Guanghui Lan (2019). A Note on Inexact Condition for CubicRegularized Newton’s Method. Operations Research Letters.
Published, 08/01/2019.
- Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang & Vahid Tarokh (2019). Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization. International Conference on Machine Learning (ICML).
Published, 07/01/2019.
Presentations
- Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization (IJCAI).
Conference Paper, Refereed,
Presented, 01/15/2021.
- Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study. Cheng Chen, Junjie Yang, Yi Zhou. IEEE Bigdata 2020.
Conference Paper, Refereed,
Presented, 12/10/2020.
- FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling. Cheng Chen, Ziyi Chen, Yi Zhou, Bhavya Kailkhura. IEEE Bigdata 2020.
Conference Paper, Refereed,
Presented, 12/10/2020.
- Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis. Shaocong Ma, Yi Zhou, Shaofeng Zou. NeurIPS 2020.
Conference Paper, Refereed,
Presented, 12/06/2020.
- Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle. Shaocong Ma, Yi Zhou. ICML 2020.
Conference Paper, Refereed,
Presented, 06/30/2020.
- Present ``SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization'' and ``Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization'' at NeurIPS 2019.
Conference Paper, Refereed,
Presented, 12/15/2019.
- Present ``SGD Converges to Global Minimum in Deep Learning via Star- convex Path'' at ICLR 2019.
Conference Paper, Refereed,
Presented, 05/06/2019.
Research Groups
- Ziyi Cheng, Graduate Student.
ECE/Ph.D..
08/15/2019 - present.
- Cheng Chen, Graduate Student.
ECE/Ph.D..
08/15/2019 - present.
- Shaocong Ma, Graduate Student.
ECE/Ph.D..
08/15/2019 - present.