Tianyi Chen

Assistant Professor,
Department of Electrical, Computer, and Systems Engineering,
Rensselaer Polytechnic Institute

chentianyi19 [AT] gmail.com;  chent18 [AT] rpi.edu

Room 6036, Jonsson Engineering Center,
110 8th Street, Troy, New York, 12180

Bio

I have been an Assistant Professor in the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute (RPI) since August 2019. In RPI, I am a member of the Rensselaer-IBM Artificial Intelligence Research Collaboration (AIRC). Prior to joining RPI, I received my doctoral degree from the University of Minnesota under the supervision of Prof. Georgios B. Giannakis. Prior to coming to the United States, I got my B.Sc. from Fudan University with the highest honors in July 2014, majoring in Communication Science and Engineering.

Dr. Chen is the inaugural recipient of the IEEE Signal Processing Society Best PhD Dissertation Award in 2020, a recipient of the NSF CAREER Award in 2021, and a recipient of the Amazon Research Award in 2022. He is also a co-author of the Best Student Paper Award at the NeurIPS Federated Learning Workshop in 2020, the IEEE Signal Processing Society Flagship Conference ICASSP in 2021, and the IEEE Signal Processing Society Young Author Best Paper Award in 2024.

Research interests: I was trained with a statistical signal processing, wireless communication, and optimization background, and I have a strong interest in bridging my basic theoretical research with emerging engineering applications. More recently, my research addresses the theoretical and algorithmic aspects of bileve optimization [AISTATS'22, MAPR'25], multi-objective optimization [ICLR'23, JMLR'24], and applications to

Prospective Students

• I am always looking for self-motivated students and postdocs working in the areas of machine learning, optimization, and wireless networks. Students with strong analytical skills and interests in theory and application of optimization in AI and computing areas would be a great fit. • Please email me if you're interested, but I don't promise a response. You can apply to the Electrical Engineering or Computer Science Engineering PhD programs at RPI, and mention me in your application.

News

Dec 2024. Our early work back to 2020 on Byzantine-resilient federated learning has been honored with the IEEE Signal Processing Society Young Author Best Paper Award (more info).

Dec 2024. Our extended study of the ICML 2023 paper on the penalty-based bilevel optimization methods has been accepted to Mathematical Programming (Series A): On Penalty-based Bilevel Gradient Descent Method (more info).

Nov 2024. I am honored to be invited to Portuguese American Optimization Workshop (PAOW), colocated with MOPTA 2025 (more info).

Oct 2024. I serve as an Area Chair for AISTATS 2025, ICLR 2025, ICML 2025, and the newly founded CPAL 2025 (more info).

Oct 2024. Three papers from our group have been accepted to the main conference of NeurIPS 2024 (more info).

Sep 2024. I am invited to present our work at The Foundations of Information, Networks, and Decision Systems (FIND) Seminar, Cornell University (more info).

Sep 2024. I am invited to serve as an Associate Editor for IEEE Transactions on Signal Processing. (more info).

Sep 2024. I am invited to present our work on the theory of analog in-memory training at The CPCC Seminar, at University of California, Irvine, and The Engineering Seminar, at King's College London (more info).

Aug 2024. We are excited to receive a new collaborative NSF project with UCI on bilevel optimization for graph representation learning (more info).

Jul 2024. Our paper on using the In-Context Learning ability of LLM for wireless symbol detection problems has been accepted to GLOBECOM 2024 (more info).

Jun 2024. My Ph.D. student Lisha Chen will join the Department of Electrical and Computer Engineering, University of Rochester in 2025 as a tenure-track Assistant Professor! (more info).

Sep 2024. I presented a tutorial on the foundation of bilevel learning and its application to LLMs at MLSP 2024, London, UK (more info).

May 2024. Two papers have been accepted to ICML 2024 and one paper has been accepted to JMLR; see recent papers (more info).

Apr 2024. We presented a tutorial at ICASSP 2024 on Learning with Multiple Objectives and Applications to Speech Processing (more info).

Mar 2024. I am invited to present our work at the Department of Electrical and Computer Engineering, Rutgers University. (more info).

Feb 2024. We presented a tutorial at AAAI 2024 on Learning with Multiple Objectives and Applications to Reinforcement Learning (more info).

Jan 2024. One paper has been accepted to AISTATS 2024; see recent papers (more info).

Oct 2023. I am invited to present our work at the Department of Electrical and Computer Engineering, Northeastern University. (more info).

Oct 2023. I am invited to serve as an Area Chair for AISTATS 2024 and CPAL 2024. (more info).

Sep 2023. Two papers have been accepted to NeurIPS 2023; see recent papers. (more info).

Sep 2023. I am invited to present our work on multi-objective learning at a departmental seminar from the Department of Industrial and Systems Engineering, Lehigh University. (more info).

Aug 2023. Our paper on lazy query for zeroth-order optimization has been accepted in TSP; see recent papers. (more info).

Jun 2023. I am invited to present our work on bilevel optimization at SIAM Conference on Optimization and MOPTA. (more info).

Apr 2023. One paper on the inexact penalization method for bilevel optimization has been accepted in ICML 2023; see recent papers. (more info).

Apr 2023. Our paper on linear speedup analysis of the popular A3C algorithm in RL has been accepted in TSP; see recent papers. (more info).

Feb 2023. Our paper on ensemble methods for bilevel learning was accepted in ICASSP 2023; see recent papers. (more info).

Feb 2023. I am invited to present our work on bilevel optimization for distributed learning at EnCORE workshop at ITA 2023. (more info).

Jan 2023. One paper has been selected as an oral paper (notable-top-5%) in ICLR 2023; see recent papers. (more info).

Jan 2023. Two papers have been accepted to AISTATS 2023; see recent papers. (more info).

Dec 2022. With Atlas Wang, we will present a tutorial at ICASSP 2023 on Bilevel Optimization and Its Applications to Machine Learning. (more info).

Nov 2022. We are honored to receive the Faculty Research Gifts from Cisco Research. (more info).

Nov 2022. We are happy to receive several IBM-RPI AI research projects, part of the IBM AI Horizons Network. (more info).

Oct 2022. Our monograph with Osvaldo's group on Meta Learning and Applications to Communications is published in Foundations and Trends in Signal Processing. (more info).

Oct 2022. We are honored to receive the Amazon Research Award - AWS AI. (more info).

Sep 2022. Two papers have been accepted to NeurIPS 2022 with one being selected as an oral presentation; see recent papers. (more info).

Sep 2022. I am invited to serve as an Area Chair for AISTATS 2023. (more info).

Aug 2022. We have organized a Cross-Community Federated Learning (CrossFL) workshop at MLSys 2022. (more info).

May 2022. Our paper has been accepted to ICML 2022; see recent papers. (more info).

Jan 2022. Two papers have been accepted to AISTATS 2022 with one being selected as an oral presentation; see recent papers. (more info).

Dec 2021. I will co-organize a workshop at MLSys 2022 with Pin-Yu Chen, Carlee Joe-Wong, and Nathalie Baracaldo on Cross-Community Federated Learning: Algorithms, Systems and Co-designs. (more info).

Nov 2021. I will co-present a tutorial at ICASSP 2022 with Prof. Osvaldo Simeone on Meta Learning and Applications to Communications. (more info).

Sep 2021. Two papers have been accepted to NeurIPS 2021 with one being selected as a spotlight presentation; see recent papers. (more info).

Sep 2021. Our paper was accepted in IEEE Trans on Pattern Analysis and Machine Intelligence; see recent papers. (more info).

Sep 2021. I am invited to the Panel Session of the Distributed ML workshop co-located with ACM CoNEXT 2021. (more info).

Sep 2021. With Derya Malak, we are organizing a workshop on Wireless Distributed Computing and Learning at WiOPT 2021. (more info).

Aug 2021. I am excited to collaborate with Rongjie Lai (RPI) and Jie Chen (MIT-IBM AI Lab) for the NSF SCALE MoDL Program on: Representation Learning via Variational Mean Field Theory. (more info).

Jul 2021. Our paper was accepted in IEEE Transactions on Signal Processing; see recent papers. (more info).

Jun 2021. Our paper was recognized as the Outstanding Student Paper Award for ICASSP 2021. (more info).

Jun 2021. Two papers were accepted in IEEE Transactions on Signal Processing; see recent papers. (more info).

May 2021. I am honored to receive the NSF CAREER Award on: The Co-design of Distributed Machine Learning Algorithms and Wireless Systems. (more info).

Apr 2021. Our paper was accepted in IEEE Transactions on Control of Network systems; see recent paper. (more info).

Jan 2021. Our papers were accepted in ICASSP 2021 on meta learning and reinforcement learning; see recent papers. (more info).

Jan 2021. Our paper was accepted in AISTATS 2021; see recent papers. (more info).

Jan 2021. My Ph.D dissertation was recognized as the inaugural IEEE SPS Best PhD Dissertation Award: Efficient Methods for Distributed Machine Learning and Resource Management in IoT. (more info).

Dec 2020. Our paper was accepted in AAAI 2021; see recent papers. (more info).

Dec 2020. Our paper was recognized as the Best Student Paper Award at NeurIPS 2020 workshop on Federated Learning: Hybrid Federated Learning: Algorithms and Implementation. (more info).

Dec 2020. Our paper was accepted in IEEE Trans on Pattern Analysis and Machine Intelligence; see recent papers. (more info).

May 2020. New paper on Byzantine-robust federated learning has been accepted in IEEE Transactions on Signal Processing; see recent papers. (more info).

Mar 2020. I am organizing the special session Reinforcement learning for communication systems at Asilomar 2020. (more info).

Dec 2019. Presented our work on Lazily Aggregated Quantized Gradients at NeurIPS 2019. (more info).

Oct 2019. Our paper has been accepted in IEEE Transactions on Signal Processing; see recent papers. (more info).

Sept 2019. Our paper was accepted at NeurIPS 2019; see recent papers. (more info).

Aug 2019. I am excited to join the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute. (more info).

Publications

Most recent publications on Google Scholar .

On Penalty-based Bilevel Gradient Descent Method.

Han Shen, Quan Xiao and Tianyi Chen.

Mathematical Programming (MAPR), to appear, pp. 1-38, 2025.

Shorter version in International Conference on Machine Learning (ICML), Honolulu, HI, July 22-29, 2023.

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance.

Lisha Chen, Heshan Fernando, Yiming Ying, and Tianyi Chen.

Journal of Machine Learning Research (JMLR), vol 25, pp. 1-53, 2024.

Shorter version in Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 10-16, 2023.

Towards Exact Gradient-based Training on Analog In-memory Computing.

Zhaoxian Wu, Tayfun Gokmen, Malte J. Rasch and Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems.

Tianyi Chen, Yuejiao Sun and Wotao Yin.

Proc. of Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021. (Spotlight).

Catastrophic Data Leakage in Vertical Federated Learning.

Xiao Jin, Pin-Yu Chen, Chia-Yi Hsu, Chia-Mu Yu, and Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021.

LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning.

Tianyi Chen, Georgios B. Giannakis, Tao Sun and Wotao Yin.

Proc. of Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021.

Towards Exact Gradient-based Training on Analog In-memory Computing.

Zhaoxian Wu, Tayfun Gokmen, Malte J. Rasch and Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning.

Lisha Chen, AFM Saif, Yanning Shen, Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints.

Liuyuan Jiang, Quan Xiao, Victor M Tenorio, Fernando Real-Rojas, Antonio G Marques, Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition.

X. Cui, AFM Saif, S. Lu, L. Chen, T. Chen, B. Kingsbury, and G. Saon.

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), December 2024.

Large Language Models for Wireless Symbol Detection via In-Context Learning.

M. Abbas, K. Kar, and T. Chen.

Proc. of IEEE Global Comm. Conf. (Globecom), Cape Town, South Africa, December 6 - 10, 2024.

Enhancing In-context Learning via Linear Probe Calibration.

Momin Abbas, Yi Zhou, Parikshit Ram, Nathalie Baracaldo, Horst Samulowitz, Theodoros Salonidis, Tianyi Chen.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, May 2-4, 2024.

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF.

Han Shen, Zhuoran Yang, Tianyi Chen.

Proc. of Intl. Conf. on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024.

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning.

Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang.

Proc. of Intl. Conf. on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024.

M2ASR: Multilingual Multi-Task Automatic Speech Recognition via Multi-Objective Optimization.

AFM Saif, L. Chen, X. Cui, S. Lu, B. Kingsbury, and T. Chen.

Proc. of Intl. Conf. of the International Speech Communication Association (Interspeech), Kos Island, Greece, September 1 - 5, 2024.

Three-way trade-off in multi-objective learning: Optimization, generalization and conflict-avoidance.

Lisha Chen, Heshan Fernando, Yiming Ying, Tianyi Chen.

Journal of Machine Learning Research (JMLR), vol 25, pp. 1-53, 2024.

Shorter version in Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 10-16, 2023.

An alternating optimization method for bilevel problems under the Polyak-Łojasiewicz condition.

Quan Xiao, Songtao Lu, Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 10-16, 2023.

On Penalty-based Bilevel Gradient Descent Method.

Han Shen, Q. Xiao, and T. Chen.

Mathematical Programming (MAPR), to appear, pp. 1-38, 2025.

Shorter version in International Conference on Machine Learning (ICML), Honolulu, HI, July 22-29, 2023.

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach.

H. Fernando, H. Shen, M. Liu, S. Chaudhury, K. Murugesan, and T. Chen.

Proc. of Intl. Conf. on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023. (Oral presentation)

On Penalty-based Bilevel Gradient Descent Method.

Han Shen, Quan Xiao and Tianyi Chen.

Mathematical Programming (MAPR), to appear, pp. 1-38, 2025.

Shorter version in International Conference on Machine Learning (ICML), Honolulu, HI, July 22-29, 2023.

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance.

Lisha Chen, Heshan Fernando, Yiming Ying, and Tianyi Chen.

Journal of Machine Learning Research (JMLR), vol 25, pp. 1-53, 2024.

Shorter version in Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 10-16, 2023.

Towards Exact Gradient-based Training on Analog In-memory Computing.

Zhaoxian Wu, Tayfun Gokmen, Malte J. Rasch and Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems.

Tianyi Chen, Yuejiao Sun and Wotao Yin.

Proc. of Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021. (Spotlight).

Catastrophic Data Leakage in Vertical Federated Learning.

Xiao Jin, Pin-Yu Chen, Chia-Yi Hsu, Chia-Mu Yu, and Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021.

LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning.

Tianyi Chen, Georgios B. Giannakis, Tao Sun and Wotao Yin.

Proc. of Neural Information Processing Systems (NeurIPS), Virtual, December 6-14, 2021.

FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning.

Lisha Chen, AFM Saif, Yanning Shen, Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints.

Liuyuan Jiang, Quan Xiao, Victor M Tenorio, Fernando Real-Rojas, Antonio G Marques, Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 9-15, 2024.

Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition.

X. Cui, AFM Saif, S. Lu, L. Chen, T. Chen, B. Kingsbury, and G. Saon.

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), December 2024.

A Bilevel Optimization Method for Inverse Mean-Field Games.

J. Yu, Q. Xiao, T. Chen, and R. Lai.

Inverse Problems, September 2024.

Large Language Models for Wireless Symbol Detection via In-Context Learning.

M. Abbas, K. Kar, and T. Chen.

Proc. of IEEE Global Comm. Conf. (Globecom), Cape Town, South Africa, December 6 - 10, 2024.

Transferable Learning of GCN Sampling Graph Data Clusters from Different Power Systems.

T. Wu, A. Scaglione, D. Arnold, and T. Chen.

Proc. of Annual Allerton Conf. Communication, Control, and Computing (Allerton), Urbana, IL, September 25 - 27, 2024.

Enhancing In-context Learning via Linear Probe Calibration.

Momin Abbas, Yi Zhou, Parikshit Ram, Nathalie Baracaldo, Horst Samulowitz, Theodoros Salonidis, Tianyi Chen.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, May 2-4, 2024.

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF.

Han Shen, Zhuoran Yang, Tianyi Chen.

Proc. of Intl. Conf. on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024.

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning.

Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang.

Proc. of Intl. Conf. on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024.

M2ASR: Multilingual Multi-Task Automatic Speech Recognition via Multi-Objective Optimization.

AFM Saif, L. Chen, X. Cui, S. Lu, B. Kingsbury, and T. Chen.

Proc. of Intl. Conf. of the International Speech Communication Association (Interspeech), Kos Island, Greece, September 1 - 5, 2024.

Joint Unsupervised and Supervised Training for Automatic Speech Recognition.

AFM Saif, X. Cui, H. Shen, S. Lu, B. Kingsbury, and T. Chen.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, Korea, April 14 - 19, 2024.

Variance Reduction Can Improve Trade-Off In Multi-Objective Learning.

H. Fernando, L. Chen, S. Lu, P.-Y. Chen, M. Liu, S. Chaudhury, K. Murugesan, G. Liu, M. Wang, and T. Chen.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, Korea, April 14 - 19, 2024.

A Method for Bilevel Optimization With Convex Lower-Level Problems.

H. Shen, S. Paternain, G. Liu, R. Kompella, and T. Chen.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, Korea, April 14 - 19, 2024.

Three-way trade-off in multi-objective learning: Optimization, generalization and conflict-avoidance.

Lisha Chen, Heshan Fernando, Yiming Ying, Tianyi Chen.

Journal of Machine Learning Research (JMLR), vol 25, pp. 1-53, 2024.

Shorter version in Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 10-16, 2023.

An alternating optimization method for bilevel problems under the Polyak-Łojasiewicz condition.

Quan Xiao, Songtao Lu, Tianyi Chen.

Proc. of Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 10-16, 2023.

On Penalty-based Bilevel Gradient Descent Method.

Han Shen, Q. Xiao, and T. Chen.

Mathematical Programming (MAPR), to appear, pp. 1-38, 2025.

Shorter version in International Conference on Machine Learning (ICML), Honolulu, HI, July 22-29, 2023.

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach.

H. Fernando, H. Shen, M. Liu, S. Chaudhury, K. Murugesan, and T. Chen.

Proc. of Intl. Conf. on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023. (Oral presentation)

Alternating Implicit Projected SGD and Its Efficient Variants for Equality-Constrained Bilevel Optimization.

Q. Xiao, H. Shen, W. Yin, and T. Chen.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, April 25-27, 2023.

Distributed Offline Policy Optimization Over Batch Data.

H. Shen, S. Lu, X. Cui, and T. Chen.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, April 25-27, 2023.

Lazy Queries Can Reduce Variance in Zeroth-order Optimization.

Q. Xiao, Q. Ling, and T. Chen.

IEEE Transactions on Signal Processing (TSP), vol. 71, December 2023.

Byzantine-Resilient Decentralized Stochastic Optimization With Robust Aggregation Rules.

Z. Wu, Q. Ling, and T. Chen.

IEEE Transactions on Signal Processing (TSP), vol. 71, pp. 3179 - 3195, August 2023.

Towards Understanding Asynchronous Advantage Actor-Critic: Convergence and Linear Speedup.

H. Shen, K. Zhang, M. Hong, and T. Chen.

IEEE Transactions on Signal Processing (TSP), vol. 71, pp. 2579 - 2594, May 2023.

A Method for Bilevel Optimization with Convex Lower-Level Problems.

H. Shen, S. Paternain, and T. Chen.

Proc. of Asilomar Conf. on Signals, Systems, & Computers, Pacific Grove, October 29 - November 1, 2023.

A Nested Ensemble Method to Bilevel Machine Learning.

L. Chen, M. Abbas, and T. Chen.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes Island, Greece, June 4 - 10, 2023.

Understanding Benign Overfitting in Meta-Learning.

L. Chen, S. Lu, and T. Chen.

Proc. of Neural Information Processing Systems (NeurIPS), New Orleans, LA, November 28 - December 9, 2022.

A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences.

H. Shen and T. Chen.

Proc. of Neural Information Processing Systems (NeurIPS), New Orleans, LA, November 28 - December 9, 2022. (Oral presentation, Top 1.5% of all submitted papers)

Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning.

M. Abbas, Q. Xiao, L. Chen, P.-Y. Chen, and T. Chen.

Proc. of Intl. Conf. on Machine Learning (ICML), Baltimore, MD, July 17-23, 2022.

Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees.

S. Zeng, T. Chen, A. Garcia, and M. Hong.

Proc. of Learning for Dynamics and Control Conference (L4DC), Palo Alto, CA, June 2022.

Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably.

L. Chen and T. Chen.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Virtual, March 28-30, 2022.

A Single-Timescale Stochastic Optimization Method for Stochastic Bilevel Problems.

T. Chen, Y. Sun, Q. Xiao, and W. Yin.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Virtual, March 28-30, 2022. (Oral presentation, Top 2% of all submitted papers)

Understanding Benign Overfitting in Personalized Federated Learning.

L. Chen and T. Chen.

Proc. of European Signal Processing Conf. (EUSIPCO), Belgrade, Serbia, August 29 - September 2, 2022.

Federated Multi-Armed Bandit Via Uncoordinated Exploration.

Z. Yan, Q. Xiao, T. Chen, and A. Tajer.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Singapore, May 23 - 27, 2022.

CADA: Communication-Adaptive Distributed Adam.

T. Chen, Z. Guo, Y. Sun, and W. Yin.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Virtual, April 16-18, 2021.

Decentralized Policy Gradient Descent Ascent For Safe Multi-Agent Reinforcement Learning.

S. Lu, K. Zhang, T. Chen, T. Basar, and L. Horesh.

Proc. of AAAI Conf. on Artificial Intelligence (AAAI), Virtual, February 2-9, 2021.

Solving Stochastic Compositional Optimization Is Nearly As Easy As Solving Stochastic Optimization.

T. Chen, Y. Sun, and W. Yin.

IEEE Transactions on Signal Processing (TSP), vol. 69, pp. 4937 - 4948, June 2021.

Adaptive Temporal Difference Learning with Linear Function Approximation.

T. Sun, H. Shen, T. Chen, and D. Li.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear, 2021.

Communication-Adaptive Stochastic Gradient Methods for Distributed Learning.

T. Chen, Y. Sun, and W. Yin.

IEEE Transactions on Signal Processing (TSP), vol. 69, pp. 4637 - 4651, July 2021.

Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation.

Z. Wu, H. Shen, T. Chen, and Q. Ling.

IEEE Transactions on Signal Processing (TSP), vol. 69, pp. 3839 - 3853, June 2021.

Multi-Agent Multi-Armed Bandit Learning for Online Management of Edge-Assisted Computing.

B. Wu, T. Chen, W. Ni, and X. Wang.

IEEE Transactions on Communications (TCOM), to appear, 2021.

Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning.

T. Chen, K. Zhang, G. Giannakis, and T. Basar.

IEEE Transactions on Control of Network Systems (TCNS), 2021.

Lazily Quantized Gradient Innovation for Communication-Efficient Federated Learning.

J. Sun, T. Chen, G. Giannakis, and Z. Yang.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear, 2021.

Federated Offline Policy Evaluation Over Distributed Batch Datasets.

H. Shen, X. Li, S. Lu, and T. Chen.

Proc. of Asilomar Conf. on Signals, Systems, & Computers, Virtual, October 31 - November 3, 2021.

An Optimal Stochastic Compositional Optimization Method with Applications to Meta Learning.

Y. Sun, T. Chen, and W. Yin.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), June 6 - 11, 2021.

Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation.

Z. Wu, H. Shen, T. Chen, and Q. Ling.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), June 6 - 11, 2021.

Hybrid Federated Learning: Algorithms and Implementation.

X. Zhang, W. Yin, M. Hong, and T. Chen.

NeurIPS Workshop on Scalability, Privacy, and Security in Federated Learning, December 12, 2020.

VAFL: a Method of Vertical Asynchronous Federated Learning.

T. Chen, X. Jin, Y. Sun, and W. Yin.

Proc. of ICML Workshop on Federated Learning for User Privacy and Data Confidentiality, July 17-18, 2020.

Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks.

Z. Wu, Q. Ling, T. Chen, and G. B. Giannakis.

IEEE Transactions on Signal Processing (TSP), vol. 68, pp. 4583 - 4596, July 2020.

A Combinatorial Bandit Approach to UAV-Aided Edge Computing.

B. Wu, T. Chen, and X. Wang.

Proc. of Asilomar Conf. on Signals, Systems, & Computers, Pacific Grove, CA, November 1 - 5, 2020.

An MAB Approach for MEC-Centric Task-Offloading Control in Multi-RAT HetNets.

B. Wu, T. Chen, and X. Wang.

Proc. of International Conference on Communications (ICC), Virtual, June 7 - 11, 2020.

Resilient to Byzantine Attacks Finite-Sum Optimization over Networks.

Z. Wu, Q. Ling, T. Chen, and G. B. Giannakis.

Proc. of Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, May 4 - 9, 2020.

Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients.

J. Sun*, T. Chen*, G. Giannakis, and Z. Yang. (*equal contribution)

Proc. of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.

Bandit Online Learning with Unknown Delays.

B. Li, T. Chen, and G. B. Giannakis.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Naha, Japan, April 16-18, 2019.

RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets.

L. Li, W. Xu, T. Chen, G. B. Giannakis, and Q. Ling.

Proc. of AAAI Conf. on Artificial Intelligence (AAAI), Honolulu, USA, January 27 - February 1, 2019.

Secure Mobile Edge Computing in IoT via Collaborative Online Learning.

B. Li, T. Chen, and G. B. Giannakis.

IEEE Transactions on Signal Processing (TSP), vol. 67, no. 23, pp. 5922 - 5935, December 2019.

Learning and Management for Internet-of-Things: Accounting for Adaptivity and Scalability.

T. Chen, S. Barbarossa, X. Wang, G. B. Giannakis, and Z.-L. Zhang.

Proceedings of the IEEE (PIEEE), vol. 107, no. 4, pp. 778 - 796, April 2019.

Random Feature-based Online Multi-Kernel Learning in Environments with Unknown Dynamics.

Y. Shen, T. Chen, and G. B. Giannakis.

Journal of Machine Learning Research (JMLR), vol. 20, no. 22, pp. 1 - 36, February 2019.

Real-Time Optimal Energy Management with Reduced Battery Capacity Requirements.

B. Li, T. Chen, X. Wang, and G. B. Giannakis.

IEEE Transactions on Smart Grid (TSG), vol. 10, no. 2, pp. 1928 - 1938, February 2019.

Bandit Convex Optimization for Scalable and Dynamic IoT Management.

T. Chen and G. B. Giannakis.

IEEE Internet of Things J. (JIOT), vol. 6, no. 1, pp. 1276 - 1286, February 2019.

Online Ensemble Multi-kernel Learning Adaptive to Non-stationary and Adversarial Environments.

Y. Shen, T. Chen, and G. B. Giannakis.

Proc. of Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), Lanzarote, Canary Islands, April 9 - 11, 2018.

Learn-and-Adapt Stochastic Dual Gradients for Network Resource Allocation.

T. Chen, Q. Ling, and G. B. Giannakis.

IEEE Transactions on Control of Network Systems (TCNS), vol. 5, no. 4, pp. 1941 - 1951, December 2018.

Heterogeneous Online Learning for 'Thing-Adaptive' Fog Computing in IoT.

T. Chen, Q. Ling, Y. Shen, and G. B. Giannakis.

IEEE Internet of Things J. (JIOT), vol. 5, no. 6, pp. 4328 - 4341, December 2018.

Secure Edge Computing in IoT via Online Learning.

B. Li, T. Chen, X. Wang, and G. B. Giannakis.

Proc. of Asilomar Conf. on Signals, Systems, & Computers, Pacific Grove, CA, October 28 - 31, 2018.

Aggregating Flexibility of Heterogeneous Energy Resources in Distribution Networks.

T. Chen, N. Li, and G. B. Giannakis.

Proc. of American Control Conference (ACC), Milwaukee, WI, June 27 - 29, 2018.

Harnessing Bandit Online Learning for Low-Latency Fog Computing.

T. Chen and G. B. Giannakis.

Proc. of Intl. Conf. on Acoust., Speech, and Signal Processing (ICASSP), Calgary, Canada, April 15 - 20, 2018.

Online Multi-Kernel Learning with Orthogonal Random Features.

Y. Shen, T. Chen, and G. B. Giannakis.

Proc. of Intl. Conf. on Acoust., Speech, and Signal Processing (ICASSP), Calgary, Canada, April 15 - 20, 2018.

An Online Convex Optimization Approach to Proactive Network Resource Allocation.

T. Chen, Q. Ling, and G. B. Giannakis.

IEEE Transactions on Signal Processing (TSP), vol. 65, no. 24, pp. 6350 - 6364, December 2017.

Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation.

T. Chen, A. Mokhtari, X. Wang, A. Ribeiro, and G. B. Giannakis.

IEEE Transactions on Signal Processing (TSP), vol. 65, no. 12, pp. 3078 - 3093, June 2017.

Real-Time Energy Management with Improved Cost-Capacity Tradeoff.

B. Li, T. Chen, X. Wang, and G. B. Giannakis.

Proc. of IEEE Global Conf. on Signal and Info. Processing (GlobalSIP), Montreal, Canada, November 14 - 16, 2017.

Online Learning for 'Thing-Adaptive' Fog Computing in IoT.

T. Chen, Y. Shen, Q. Ling, and G. B. Giannakis.

Proc. of Asilomar Conf. on Signals, Systems, & Computers (Asilomar), Pacific Grove, CA, October 29 - November 1, 2017.

Online Convex Optimization for Dynamic Network Resource Allocation.

T. Chen, Q. Ling, and G. B. Giannakis.

Proc. of European Signal Processing Conf. (EUSIPCO), Kos Island, Greece, August 28 - September 3, 2017.

Learn-and-Adapt Network Resource Allocation.

T. Chen, Q. Ling, and G. B. Giannakis.

Proc. of IEEE Signal Processing Advances in Wireless Communications (SPAWC), Hokkaido, Japan, July 3 - 6, 2017.

Dynamic Resource Allocation for Smart-Grid Powered MIMO Downlink Transmissions.

X. Wang, T. Chen, X. Chen, X. Zhou, and G. B. Giannakis.

IEEE J. on Selected Areas in Communications (JSAC), vol. 34, no. 12, pp. 3354 - 3365, December 2016.

Robust Workload and Energy Management for Sustainable Data Centers.

T. Chen, Y. Zhang, X. Wang, and G. B. Giannakis.

IEEE J. on Selected Areas in Communications (JSAC), vol. 34, no. 3, pp. 651-654, March 2016.

Cooling-Aware Energy and Workload Management in Data Centers via Stochastic Optimization.

T. Chen, X. Wang, and G. B. Giannakis.

IEEE J. on Special Topics in Signal Processing (JSTSP), vol. 10, no. 2, pp. 402-405, March 2016.

A Data-Driven Approach to Stochastic Network Optimization.

T. Chen, A. Mokhtari, X. Wang, A. Ribeiro, and G. B. Giannakis.

Proc. of IEEE Global Conf. on Signal and Info. Processing (GlobalSIP), Washington, DC, December 7 - 9, 2016.

Two-Scale Stochastic Control for Smart-Grid Powered Coordinated Multi-Point Systems.

X. Chen, T. Chen, X. Wang, L. Huang, and G. B. Giannakis.

Proc. of IEEE Global Comm. Conf. (Globecom), Washington, DC, December 4 - 8, 2016.

Robust Geographical Load Balancing for Sustainable Data Centers.

T. Chen, Y. Zhang, X. Wang, and G. B. Giannakis.

Proc. of Intl. Conf. on Acoust., Speech, and Signal Processing (ICASSP), Shanghai, China, March 20 - 25, 2016.

Optimal Scheduling for Wireless On-Demand Data Packet Delivery to High-Speed Trains.

T. Chen, H. Shan, and X. Wang.

IEEE Transactions on Vehicular Technology (TVT), vol. 64, no. 9, pp. 4101-4112, September 2015.

Energy and Workload Management for Data Centers in Renewable-Integrated Power Grid.

T. Chen, X. Wang, and G. B. Giannakis.

Proc. of IEEE Global Conf. on Signal and Info. Processing (GlobalSIP), Orlando, FL, December 14 - 16, 2015.

Dynamic Power Management for Green Coordinated Multipoint Systems.

X. Wang, T. Chen, Y. Zhang, and G. B. Giannakis.

Proc. of IEEE Global Comm. Conf. (Globecom), San Diego, CA, December 6 - 10, 2015.

Packet Scheduling for On-Demand Data Services to High-Speed Trains over Wireless Links.

T. Chen, H. Shan, and X. Wang.

Proc. of IEEE Global Comm. Conf. (Globecom), Atlanta, GA, December 9 - 13, 2013.

People

Lisha Chen
2021 Summer - 2025 Spring
B.S. Huazhong University of Science and Technology, China

Heshan Fernando
2021 Summer - present
B.S. University of Moratuwa,
Sri Lanka

Liuyuan Jiang
2023 Fall - present
M.S. Cornell University
B.S. Xi'an Jiaotong-Liverpool U.

Jindan Li
2024 Fall - present
B.S. Zhejiang University, Hangzhou, China

A F M Saif
2023 Fall - present
B.S. Bangladesh University of Engineering and Technology

Quan Xiao
2021 Fall - present
B.S. University of Science and Technology of China, Hefei, China

Zhaoxian Wu
2023 Fall - present
M.S. Sun Yat-sen University
B.S. Sun Yat-sen University, Guangzhou, China

Han Shen
2020 Spring - 2024 Fall
Ph.D. Rensselaer Polytechnic Institute (RPI)
B.S. Shanghai University, China

Momin Abbas
2021 Spring - 2024 Spring
M.S. RPI
B.S. National Uni. of Sciences and Technology, Pakistan

Xiao Jin
2019 Fall - 2021 Fall
M.S. RPI
B.S. Fudan University, Shanghai, China

Xuefei Li
2021 Fall - 2023 Spring
M.S. RPI
B.S. Fudan University, Shanghai, China

Ziye Guo
2019 Fall - 2021 Spring
M.S. RPI
B.S. Beijing Uni. of Posts and Telecomm., China

Awards

2024. IEEE Signal Processing Society Young Author Best Paper Award (more info).

2023 and 2024. Cisco Research Award (more info).

2022. Amazon Research Award - AWS AI (more info).

2021. National Science Foundation CAREER Award (more info).

2021. Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP) Best Student Paper Award (more info).

2020. IEEE Signal Processing Society Best PhD Dissertation Award (more info).

2020. Best Student Paper Award, NeurIPS workshop on Federated Learning (NeurIPS-SpicyFL) (more info).

2017. Doctoral Dissertation Fellowship, University of Minnesota (more info).

2017. Asilomar Conference Best Student Paper Award Finalist (more info).

2014. Dr. Krzysztof K. Burhardt and April L. Spas Fellowship, University of Minnesota (more info).

Experiences

Acknowledgments

Acknowledgment: National Science Foundation (CAREER-2047177, ECCS 2412486, SCALE-MODL 2134168/2401297), Amazon Research Award (AWS AI), IBM AI Horizons, Cisco Research, Nvidia, IEEE Signal Processing Society


This website is based on a template by Martin Saveski and Mor Naaman.