Publications

Pre-prints:

• Momentum with Variance Reduction for Nonconvex Composition Optimization. Ziyi Chen, Yi Zhou.

2024

• Model-Agnostic Meta-Learning for EEG-Based Inter-Subject Emotion Recognition. Journal of Neural Engineering 2024.

• Boosting the Performance of Reinforcement Learning-based Task Scheduling using Offline Inference. IEEE HPEC 2024.

• Reinforcement Learning-generated Topological Order for Dynamic Task Graph Scheduling. IEEE HPEC 2024.

• Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation. ICML 2024.

• Boosting One-Point Derivative-Free Online Optimization via Residual Feedback. IEEE TAC 2024.

• Large-scale Non-convex Stochastic Constrained Distributionally Robust Optimization. AAAI 2024.

• A Resource-efficient Task Scheduling System Using Reinforcement Learning. ASP-DAC 2024

• On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning. ICLR 2024.

• On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback. ICLR 2024.

2023

• Visualizing and Analyzing the Topology of Neuron Activations in Deep Adversarial Training. Youjia Zhou, Yi Zhou, Jie Ding, Bei Wang. ICML 2023.

• Online Nonconvex Optimization with Limited Instantaneous Oracle Feedback. Ziwei Guan, Yi Zhou, Yingbin Liang. COLT 2023.

• Multi-Agent Recurrent Deterministic Policy Gradient with Inter-Agent Communication (MARDPG-IAC). Joohyun Cho, Mingxi Liu, Yi Zhou, Rong-Rong Chen. Asilomar 2023.

• Assisted Unsupervised Domain Adaptation. Cheng Chen, Jiawei Zhang, Jie Ding, Yi Zhou. ISIT 2023.

• Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization. Ziyi Chen, Yi Zhou, Yingbin Liang, Zhaosong Lu. ICML 2023.

• Assisted Learning for Organizations with Limited Imbalanced Data. Cheng Chen, Jiaying Zhou, Jie Ding, Yi Zhou. TMLR 2023.

• A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization. Ziyi Chen, Qunwei Li, Yi Zhou. TMLR 2023.

• Edge-cloud Collaborative Learning with Federated and Centralized Features. Zexi Li, Qunwei Li, Yi Zhou, Wenliang Zhong, Guannan Zhang and Chao Wu. SIGIR 2023.

• An Accelerated Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization. Ziyi Chen, Yi Zhou. Machine Learning 2023.

2022

• Finding Correlated Equilibrium of Constrained Markov Game: A Primal-Dual Approach. Ziyi Chen, Shaocong Ma, Yi Zhou. NeurIPS 2022.

• Multi-Agent Off-Policy TDC with Near-Optimal Sample and Communication Complexities. Ziyi Chen, Yi Zhou, Rong-Rong Chen. TMLR 2022.

• Data-Driven Robust Multi-Agent Reinforcement Learning. Y. Wang, Y. Wang, Y. Zhou, A. Velasquez, S. Zou. MLSP 2022.

• Data Sampling Affects the Complexity of Online SGD over Dependent Data. S. Ma, Z. Chen, K. Ji, Y. Zhou, Y. Liang.  UAI 2022.

• Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis. Z. Chen, S. Zou, R. Chen, Y. Zhou. ICML 2022.

• Accelerated Proximal Alternating Gradient-Descent-Ascent for Nonconvex Minimax Machine Learning. Ziyi Chen, Shaocong Ma, Yi Zhou, ISIT 2022.

• Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov Game. Ziyi Chen, Shaocong Ma, Yi Zhou, ICLR 2022.

2021

• Communication-Free Two-Stage Multi-AgentDDPG under Partial States and Observations. Joohyun Cho, Mingxi Liu, Yi Zhou, Rong-Rong Chen, Asilomar 2021.

• Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation. Yue Wang, Shaofeng Zou, Yi Zhou, NeurIPS 2021.

• Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization. Y. Zhou, H.Zhang, Y. Liang.  Machine Learning Journal 2021

• A New One-Point Residual-Feedback Oracle For Black-Box Learning and Control. Yan Zhang, Yi Zhou, Kaiyi Ji, Michael M. Zavlanos. Automatica 2021.

• Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing. Cheng Chen, Bhavya Kailkhura, Ryan Goldhahn, Yi Zhou. IEEE MASS 2021

• MR-GAN: Manifold Regularized Generative Adversarial Networks for Scientific Data. SIAM Journal on Mathematics of Data Science

• Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry. Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang. ICLR 2021

• Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity. Shaocong Ma, Ziyi Chen, Yi Zhou, Shaofeng Zou. ICLR 2021

• Understanding Estimation and Generalization Error of Generative Adversarial Networks. Kaiyi Ji, Yi Zhou, Yingbin Liang. IEEE Transactions on Information Theory, 2021.

• When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models? Tengyu Xu, Yi Zhou, Kaiyi Ji, Yingbin Liang. Stat, 2021.

2020

• FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling. Cheng Chen, Ziyi Chen, Yi Zhou, Bhavya Kailkhura. IEEE Bigdata 2020.

• Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study. Cheng Chen, Junjie Yang, Yi Zhou. IEEE Bigdata 2020.

• Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis. Shaocong Ma, Yi Zhou, Shaofeng Zou. NeurIPS 2020.

• A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning. Bhavya Kailkhura, Yi Zhou. NeurIPS 2020.

• Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle. Shaocong Ma, Yi Zhou. ICML 2020.

• History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms. Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou, Wei Zhang, Yingbin Liang. ICML 2020.

• Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization. Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh. IJCAI2020.

• SUPERVISED ENCODING FOR DISCRETE REPRESENTATION LEARNING. Cat P. Le, Yi Zhou, Jie Ding, Vahid Tarokh. ICASSP 2020.

• Perception-Distortion Trade-off with Restricted Boltzmann Machines. Chris Cannella, Jie Ding, Mohammadreza Soltani, Yi Zhou, Vahid Tarokh. ICASSP 2020.

• Reanalysis of Variance Reduced Temporal Difference Learning. Tengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang. ICLR 2020.

2019

• Recurrent Neural Network-Assisted Adaptive Sampling for Approximate Computing. Yi Feng, Yi Zhou, Vahid Tarokh. IEEE Bigdata conference 2019.

• SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization. Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh. NeurIPS 2019. 

• Multi-level Mean-shift Clustering for Single-channel Radio Frequency Signal Separation. Yi Zhou, Yi Feng, Vahid Tarokh, Vadas Gintautas, Jessee Mcclelland, Denis Garagic. MLSP 2019.

• Distributed SGD Generalizes Well Under Asynchrony. Jayanth Regatti, Gaurav Tendolkar, Yi Zhou, Abhishek Gupta, Yingbin Liang. Allerton 2019.

• Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization. Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang, Vahid Tarokh. ICML 2019.

• Cubic Regularization with Momentum for Nonconvex Optimization . Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan. UAI 2019.

• SGD Converges to Global Minimum in Deep Learning via Star-convex Path. Yi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh. ICLR2019. 

• Toward Understanding the Impact of Staleness in Distributed Machine Learning. Wei Dai, Yi Zhou, Nanqing Dong, Hao Zhang, Eric P. Xing.  ICLR2019. 

• A Note on Inexact Condition for Cubic Regularized Newton’s Method. Z. Wang,  Y. Zhou, Y. Liang, G. Lan.  Operational Research Letters.

• Sample Complexity of Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization. Z. Wang,  Y. Zhou, Y. Liang. AISTATS 2019.

2018

• Convergence of Cubic Regularization for Nonconvex Optimization under KŁ Property. Y. Zhou, W. Zhe and Y. Liang. NeurIPS 2018.

• Distributed Proximal Gradient Algorithm for Partially Asynchronous Computer Clusters. Y. Zhou, Y. Yu, W. Dai, Y. Liang, E. Xing. JMLR 2018.

• Critical Points of Neural Networks: Analytical Forms and Landscape Properties. Y. Zhou, Yingbin Liang. In Proc. ICLR 2018.

2017

• A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms. H. Zhang, Y. Zhou, Y. Liang, and Y. Chi. JMLR 2017.

• Characterization of Gradient Dominance and Regularity Conditions for Neural Networks. Y. Zhou, Yingbin Liang. NeurIPS workshop on deep learning theory, 2017.

•  Analyzable Diversity-Promoting Latent Space Models. P. Xie, Y. Deng, Y. Zhou, A. Kumar, Y. Yu, J. Zou, E. P. Xing. ICML 2017.

• Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization. Q. Li, Y. Zhou, Y. Liang. ICML 2017.

• Demixing Sparse Signals via Convex Optimization. Y. Zhou, Y. Liang. ICASSP 2017.

2016

• Accelerated Gradient Descent for Non-convex Phase Retrieval. Y. Zhou, H. Zhang, Y. Liang. Allerton Conference 2016.

• On Compressive Orthonormal Sensing. Y. Zhou, H. Zhang, Y. Liang. Allerton Conference 2016.

• Lighter-Communication Distributed Machine  Learning via Sufficient Factor Broadcasting. P. Xie, J. Kim, Y. Zhou, Q. Ho, A. Kumar, Y. Yu, E. Xing. UAI 2016.

• On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel System. Y. Zhou, Y. Yu, W. Dai, Y. Liang, E. Xing. AISTATS 2016.

2015

• Analysis of Robust PCA via Local Incoherence. H. Zhang, Y. Zhou, Y. Liang. NeurIPS 2015.

2013

• Asymmetric-access Aware Optimization for STT-RAM Caches with Process Variations. Y. Zhou, C. Zhang, G. Sun, K. Wang, Y. Zhang. GLSVLSI 2013.