Publications

Representative/Recent Works

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

• On Penalty-based Bilevel Gradient Descent Method

  • Han Shen, Quan Xiao and Tianyi Chen

  • Mathematical Programming (MAPR), to appear, pp. 1-38, 2024.

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

  • The preliminary version has received the 2021 ICASSP Best Student Paper Award.

• 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 [Talk], [Poster], and [Code]

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

  • Proc. of Neural Information Processing Systems (NeurIPS), Montreal, Canada, December 3-8, 2018. (Spotlight)

Dissertation

• Efficient Methods for Distributed Machine Learning and Resource Management in IoT

  • Ph. D. Dissertation, University of Minnesota, Twin Cities, June 2019.

  • 2020 IEEE Signal Processing Society Best PhD Dissertation Award.

Books / monographs

• Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems

  L. Chen*, S. T. Jose*, I. Nikoloska*, S. Park*, T. Chen and O. Simeone

  Foundations and Trends in Signal Processing, 2023.

Journal papers

1. On Penalty-based Bilevel Gradient Descent Method

   • H. Shen, Q. Xiao and T. Chen

   • Mathematical Programming (MAPR), to appear, pp. 1-38, 2024.

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

   • L. Chen, H. Fernando, Y. Ying, and T. Chen

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

3. Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition

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

   • IEEE Transactions on Audio, Speech and Language Processing, to appear 2024.

4. Lazy Queries Can Reduce Variance in Zeroth-order Optimization

   • Q. Xiao, Q. Ling and T. Chen

   • IEEE Transactions on Signal Processing, vol. 71, to appear, December 2023.

5. Byzantine-resilient decentralized stochastic optimization with robust aggregation rules

   • Z. Wu, Q. Ling and T. Chen

   • IEEE Transactions on Signal Processing, vol. 71, pp. 3179 - 3195, August 2023.

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

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

   • IEEE Transactions on Signal Processing, vol. 71, pp. 2579 - 2594, May 2023.

7. 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, vol. 44, no. 12, pp. 8812 - 8824, December 2022.

8. Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning

   • T. Chen, K. Zhang, G. B. Giannakis, and T. Başar

   • IEEE Transactions on Control of Network Systems, vol. 9, no. 2, pp. 917 - 929, June 2022.

9. Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning

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

   • IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 4, pp. 2031 - 2044, April 2022.

10. LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning

    • T. Chen, Y. Sun and W. Yin

    • IEEE Transactions on Signal Processing, vol. 69, pp. 4637 - 4651, July 2021.

11. Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization

    • T. Chen, Y. Sun and W. Yin

    • IEEE Transactions on Signal Processing, vol. 69, pp. 4937 - 4948, June 2021.

12. Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation.

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

    • IEEE Transactions on Signal Processing, vol. 69, pp. 3839 - 3853, June 2021.

13. 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, vol. 68, pp. 4583-4596, December 2020.

    • 2024 IEEE Signal Processing Society Young Author Best Paper Award.

14. Secure Mobile Edge Computing in IoT via Collaborative Online Learning

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

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

15. 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, vol. 107, no. 4, pp. 778-796, April 2019.

16. 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, vol. 20, no. 22, pp. 1-36, February 2019.

17. 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, vol. 10, no. 2, pp. 1928-1938, March 2019.

18. Bandit Convex Optimization for Scalable and Dynamic IoT Management

    • T. Chen and G. B. Giannakis

    • IEEE Internet of Things Journal, vol. 6, no. 1, pp. 1276-1286, February 2019.

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

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

    • IEEE Internet of Things Journal, vol. 5 , no. 6 , pp. 4328 - 4341, December 2018.

20. 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, vol. 5, no. 4, pp. 1941-1951, December 2018.

21. Two-Scale Stochastic Control for Multipoint Communication Systems with Renewables

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

    • IEEE Transactions on Smart Grid, vol. 9, no. 3, pp. 1822 - 1834, May. 2018.

22. An Online Convex Optimization Approach to Proactive Network Resource Allocation

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

    • IEEE Transactions on Signal Processing, vol. 65, no. 24, pp. 6350-6364, Dec. 2017.

23. Real-time Energy Trading and Future Planning for Fifth-Generation Wireless Communications

    • X. Chen, W. Ni, T. Chen, I. Collins, X. Wang and G. B. Giannakis

    • IEEE Wireless Communications Magazine, vol.24, no. 4, pp. 24-30, Aug. 2017.

24. 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, vol. 65, no. 12, pp. 3078-3093, Jun. 2017.

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

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

    • IEEE Journal on Selected Areas in Communications, Vol. 34, No. 12, pp. 3354 - 3365, Dec. 2016.

26. Robust Workload and Energy Management for Sustainable Data Centers

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

    • IEEE Journal on Selected Areas in Communications, Vol. 34, No. 3, pp. 651-664, Mar. 2016.

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

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

    • IEEE Journal on Special Topics in Signal Processing, Vol. 10, No. 2, pp. 402-415, Mar. 2016.

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

    • T. Chen, H. Shan and X. Wang

    • IEEE Transaction on Vehicular Technology, Vol. 64, No. 9, pp. 4101 - 4112, Sept. 2015.

29. Optimal MIMO Broadcasting for Energy Harvesting Transmitter with Non-ideal Circuit Power Consumption

    • X. Wang, Z. Nan and T. Chen

    • IEEE Transaction on Wireless Communication, Vol. 14, No. 5, pp. 2500 - 2512, May 2015.

Selected Conference papers (not updated)

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

   • L. Chen, H. Fernando, Y. Ying, and T. Chen

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

2. A Generalized Alternating Method for Bilevel Learning under the Polyak-Lojasiewicz Condition

   • Q. Xiao, S. Lu, and T. Chen

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

3. On Penalty-based Bilevel Gradient Descent Method

   • H. Shen, Q. Xiao and T. Chen

   • Proc. of International Conference on Machine Learning (ICML), Honolulu, HI, July 22-29, 2023.

4. 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.

5. Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach (Oral)

   • 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.

6. 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.

7. 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.

8. Understanding Benign Overfitting in Gradient-based Meta Learning

   • L. Chen, S. Lu, and T. Chen

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

9. A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences (Oral)

   • H. Shen and T. Chen

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

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

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

    • Proc. of International Conference on Machine Learning (ICML), Baltimore, MD, July 17-23, 2022.

11. 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), Virtual, May 22-27, 2022.

12. 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.

13. A Single-Timescale Method for Stochastic Bilevel Optimization (Oral)

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

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

14. Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems (Spotlight)

    • T. Chen, Y. Sun and W. Yin

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

15. Catastrophic Data Leakage in Vertical Federated Learning

    • X. Jin, P.-Y. Chen, C.-Y. Hsu, C.-M. Yu, and T. Chen

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

16. A Stochastic Compositional Optimization Method with Applications to Meta Learning (Best Student Paper)

    • Y. Sun, T. Chen, and W. Yin

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

17. 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.

18. Decentralized policy gradient descent ascent for safe multi-agent reinforcement learning

    • S. Lu, K. Zhang, T. Chen, T. Başar, and L. Horesh,

    • Proc. of the Assoc. for the Advanc. of Artificial Intelligence (AAAI), Virtual, February 2-9, 2021.

19. Hybrid Federated Learning: Algorithms and Implementation (Best Student Paper)

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

    • Proc. of NeurIPS Workshop on Scalability, Privacy, and Security in Federated Learning, Virtual, December 12, 2020.

20. 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, Virtual, July 17-18, 2020.

21. Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients

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

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

22. 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.

23. 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 the Assoc. for the Advanc. of Artificial Intelligence (AAAI), Honolulu, Hawai, January 27-February 1, 2019.

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

    • T. Chen, G. B. Giannakis, T. Sun and W. Yin

    • Proc. of Neural Information Processing Systems (NeurIPS), Montreal, Canada, December 3-8, 2018.

    • Spotlight talk, Poster, and Matlab code.

25. 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.

26. Online Learning for `Thing-Adaptive' Fog Computing in IoT (Best Student Paper Finalist)

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

    • Proc. of Asilomar Conference, Pacific Grove, CA, Oct. 29 - Nov. 1, 2017.