TIANYI CHEN

Tianyi Chen Assistant Professor Department of Electrical, Computer, and Systems Engineering Institute for Data Exploration and Applications Rensselaer Polytechnic Institute Office: Room 6036, Jonsson Engineering Center Address: 110 8th Street, Troy, New York, 12180-3590 Tel: 518-276-3173 E-mail: chent18 [@] rpi.edu Google Scholar ResearchGate

About me

Prior to joining RPI, I received my Ph.D from the University of Minnesota under the supervision of Prof. Georgios B. Giannakis.

My background is in Signal Processing and Networking. My current research focuses on the theory and applications of Optimization, Machine Learning, and Reinforcement Learning.

Notice: I am always looking for self-motivated students and visitors working in the areas of machine learning, signal processing, optimization, and wireless networks. Please drop me an email if you are interested.

Education

• University of Minnesota, Twin Cities, USA: Ph.D, Electrical and Computer Engineering, 2014.9 - 2019.6

• University of Minnesota, Twin Cities, USA: M.S., Electrical and Computer Engineering, 2014.9 - 2016.6

• Fudan University, China: B.S., Communication Science and Engineering, 2010.9 - 2014.7

Recent news

• Jan 2021: Our papers were accepted in ICASSP 2021:

  A Stochastic Compositional Optimization Method with Applications to Meta Learning
  Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation

• Jan 2021: Our paper was accepted in AISTATS 2021:

  CADA: Communication-Adaptive Distributed Adam.

• 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. [UMN News] [RPI ECSE News] [RPI News]

• Dec 2020: New paper on linear speedup analysis of the popular A3C algorithm in RL:

  Asynchronous Advantage Actor Critic: Non-asymptotic Analysis and Linear Speedup.

• Dec 2020: Our paper was accepted in AAAI 2021:

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

• Dec 2020: Our paper was accepted in NeurIPS 2020 workshop on Federated Learning:

  Hybrid Federated Learning: Algorithms and Implementation [Best Student Paper Award].

• Sept 2020: Our paper was accepted in IEEE Trans on Pattern Analysis and Machine Intelligence:

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

• Sept 2020: New paper on Byzantine-robust decentralized TD:

  Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation.

• Aug 2020: New paper on simple stochastic algorithm for learning with compositional structures (e.g., meta learning and RL):

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

• Aug 2020: I am invited to serve as a program committee member for ICLR 2021.

• Jul 2020: New paper presented in ICML Workshop on Federated Learning for User Privacy and Data Confidentiality 2020:

  VAFL: a Method of Vertical Asynchronous Federated Learning.

• May 2020: I am invited to serve as a program committee member for NeurIPS 2020.

• May 2020: New paper on Byzantine-robust federated learning has been accepted in IEEE Transactions on Signal Processing:

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

• Mar 2020: I am organizing the special session ``Reinforcement learning and bandits for communication systems'' at Asilomar 2020.

• Feb 2020: I am invited to serve as a program committee member for ICML 2020.

• Feb 2020: New paper on Lazily Aggregated Stochastic Gradients has been submitted to IEEE Transactions on Signal Processing:

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

• Feb 2020: New paper on adaptive temporal-difference learning and [Python code]:

  Adaptive Temporal Difference Learning with Linear Function Approximation.

• Jan 2020: Our paper on variance-reduced robust stochastic gradient descent has been accepted in ICASSP 2020.

• Jan 2020: I am invited to serve as a program committee member for ACM MobiHoc 2020.

• Dec 2019: Presented our work on Lazily Aggregated Quantized Gradients at NeurIPS 2019: [Paper] and [Poster]

• Oct 2019: Our paper has been accepted in IEEE Transactions on Signal Processing:

  Secure Mobile Edge Computing in IoT via Collaborative Online Learning.

• Sept 2019: New paper on finite-sample analysis of decentralized learning with Markov sampling:

  Decentralized Markov Chain Gradient Descent.

• Sept 2019: Our paper was accepted at NeurIPS 2019:

  Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients. [Python code]

• Aug 2019: I am excited to join Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute.