Home: This website is outdated. Please visit our new webpage. lilisu3.sites.northeastern.edu

e-mail: l.su@northeastern.edu or lilisu3@csail.mit.edu

Office Phone: (808)-443-3198

Address:

Northeastern, ECE

Hiring: I am always looking for excellent Ph.D. students

About me

I am an Assistant Professor in the Dept. of Electrical and Computer Engineering with a courtesy appointment in Khoury College of Computer Sciences at Northeastern University. From 2017-2020, I was a Postdoc in MIT Computer Science & Artificial Intelligence Laboratory (CSAIL). At MIT, I was very fortunate to be hosted by Prof. Nancy Lynch. I got my Ph.D degree from UIUC ECE in 2017, supervised by Prof. Nitin H. Vaidya in CSL Reliable and High Performance Computing. Before that I spent two wonderful years working with Prof. Olgica Milenkovic as a master student, and got my MS degree in August 2014 from CSL Signals, Inference, and Networks at UIUC ECE. My department profile can be found department profile

Here are my CV and Google Scholar profile

Research interests

• • Adversary-resilient distributed learning

  • Fault-tolerance and security

  • Neural computation

  • Neural networks

  • Bio-inspired distributed algorithms

  • Multi-agent optimization and consensus

CSoI Student Project Team Leader

"Machine Learning Security"

Center for Science of Information (National Science Foundation), Sept. 2016 - Present

Service

I am/was on the TPC of

• • ACM Symposium on Principles of Distributed Computing(PODC), 2022

  • ACM SIGMETRICS/IFIP Performance, 2022

  • EATCS International Symposium on Distributed Computing (DISC), 2021

  • IEEE International Conference on Distributed Computing Systems (ICDCS), 2021

  • ACM International Conference on Distributed Computing and Networking (ICDCN), 2020

  • IEEE International Conference on Distributed Computing Systems (ICDCS), 2018

Selected Awards and Honors

• • Best Student Paper Award Finalist (1/3)

  • The 30th International Symposium on DIStributed Computing (DISC), 2016

    • • • Best Student Paper Award

        • The 17th International Symposium on Stabilization, Safety, and Security of Distributed Systems, 2015

          • Rising Stars in EECS (2018)

            • • Sundaram Seshu International Student Fellowship

              • University of Illinois at Urbana Champaign, 2016-2017

                • (Service Award) Exemplary Reviewer

                • IEEE Transactions on Communication, 2015

              • Premium Jebsen Fellowship

                • Nankai University, China, 2010

                • National Fellowship

                • Ministry of Education, China, 2009

Publications

Journal articles

• • • L. Su and N. H. Vaidya,

    • "Byzantine-Resilient Multi-Agent Optimization,"

    • Accepted to IEEE Transactions on Automatic Control (TAC)

    • Special issue on Security and Privacy of Distributed Algorithms and Network Systems

    • L. Su and S. Shahrampour,

    • "Finite-time Guarantees for Byzantine-Resilient Distributed State Estimation with Noisy Measurements,"

    • Accepted to IEEE Transactions on Automatic Control (TAC)

    • Special issue on Security and Privacy of Distributed Algorithms and Network Systems

    • arXiv:1810.10086, Oct. 2018

    • L. Su, C-J Chang, and N. Lynch,

    • "Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits,"

    • Accepted to Neural Computation

    • arXiv:1904.10399, April. 2019

• • L. Su and J. Xu,

  • "Securing Distributed Gradient Descent in High Dimensional Statistical Learning,"

  • Accepted to ACM Measurement and Analysis of Computing Systems (2019)

  • L. Su, M. Zubeldia, and N. Lynch,

  • "Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory,"

  • Accepted to ACM Measurement and Analysis of Computing Systems (2019)

  • L. Su and N. H. Vaidya,

  • "Non-Bayesian Learning in the Presence of Byzantine Adversaries"

  • Distributed Computing, Springer, June 2018

  • (alphabetical order) Y. Chen, L. Su, and J. Xu,

  • "Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent,"

  • (ACM SIGMETRICS) ACM on Measurement and Analysis of Computing Systems, Dec. 2017

  • Also arXiv:1705.05491 May 2017

  • (alphabetical order) F. Farnoud (Hassanzadeh), Gregory J. Puleo, O. Milenkovic, and L. Su,

  • "Computing similarity distances between rankings,"

  • Discrete Applied Mathematics, Elsevier, Dec. 2017.

  • L. Su and N. H. Vaidya,

  • "Reaching Approximate Byzantine Consensus with Multi-hop Communication,"

  • Information and Computation, Elsevier, Aug. 2017;

  • Conference proceedings

    • (alphabetical order) L. Su and P. Yang,

    • "On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective,"

    • Accepted to NeurIPS 2019.

      • arXiv:1905.10826, May 2019

      • L. Su and J. Xu,

      • "Securing Distributed Gradient Descent in High Dimensional Statistical Learning,"

      • SIGMETRICS 2019, ACM

        • arXiv:1804.10140, April 2018

        • L. Su, M. Zubeldia, and N. Lynch,

        • "Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory,"

        • SIGMETRICS 2019, ACM.

          • arXiv:1811.03968, Nov. 2018

            • Remark: This work shares some overlap with our preliminary work arXiv:1802.08159 which focuses on cliques.

            • arXiv:1802.08159 is combined with this work.

        • P. Vyavahare, L. Su, and N. H. Vaidya,

        • "Distributed Learning over Time-Varying Graphs with Adversarial Agents,"

        • Fusion 2019, IEEE.

          • L. Su,

          • "On the Convergence Rate of Average Consensus and Distributed Optimization over Unreliable Networks,"

          • 52nd Asilomar Conference on Signals, Systems and Computers, 2018.

            • (alphabetical order) Y. Chen, L. Su, and J. Xu,

            • "Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent,"

            • ACM SIGMETRICS 2018.

              • H. Su, L. Su, A. Dornhaus, and N. Lynch,

              • "Ant-Inspired Dynamic Task Allocation via Gossiping,"

              • SSS 2017.

                • L. Su and N. H. Vaidya,

                • "Asynchronous non-Bayesian learning in the presence of crash failures, "

                • 18th International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS 2016), Nov. 2016.

                • L. Su and N. H. Vaidya,

                • "Robust multi-agent optimization: Coping with Byzantine agents with input redundancy,"

                • 18th International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS 2016), Nov. 2016.

                • L. Su and N. H. Vaidya,

                • "Non-Bayesian Learning in the Presence of Byzantine Adversaries"

                • International Symposium on DIStributed Computing (DISC), Sep. 2016

                • Best Student Paper Award Finalist (1/3)

                • Extended version available at "arXiv"

                • L. Su and N. H. Vaidya,

                • "Fault-Tolerant Multi-Agent Optimization: Optimal Distributed Algorithms,"

                • ACM Symposium on Principles of Distributed Computing (PODC), July 2016

                • L. Su and N. H. Vaidya,

                • "Multi-Agent Optimization in the Presence of Byzantine Adversaries: Fundamental Limits,"

                • IEEE American Control Conference (ACC), July 2016

                • L. Su and N. H. Vaidya,

                • "Reaching Approximate Byzantine Consensus with Multi-hop Communication,"

                • 17th International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS 2015), Aug. 2015.

                • Best Student Paper Award

                • Full version appeared in "arXiv", Nov. 2014

                • L. Su and O. Milenkovic,

                • "Synchronizing Rankings via Interactive Communication,"

                • IEEE International Sysmposium on Information Theory (ISIT), July 2014

                • Full version appeared in "arXiv", Feb. 2014

                • L. Su, F. Farnoud (Hassanzadeh), and O. Milenkovic,

                • "Similarity Distances Between Permutations,"

                • IEEE International Sysmposium on Information Theory (ISIT), July 2014

                • Full version appeared in "arXiv", July 2013

  • Talks and Presentations

    • Adversary-Resilience in Federated Learning

      • Invited talk at SINE/CS seminar UIUC, Nov. 2019

    • Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory,

      • Invited talk at 2019 INFORMS Annual Meeting

        • SIGMETRICS, June 2019

    • Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits,

      • 7th Workshop on Biological Distributed Algorithms, co-located with PODC, July. 2019.

    • Securing Distributed Gradient Descent in High Dimensional Statistical Learning,

      • SIGMETRICS, June 2019

    • On the Convergence Rate of Average Consensus and Distributed Optimization over Unreliable Networks,

      • Conference presentation, Asilomar, Oct. 2018.

    • Securing Distributed Machine Learning in High Dimensions,

      • Invited talk at 2nd Workshop on Storage, Control, Networking in Dynamic Systems (SCNDS), co-located with DISC 2018. Oct. 2018.

    • Decentralized Statistical Learning in Adversarial Environments: Byzantine Gradient Descent

      • Invited talk at California Institute of Technology, Jan. 2019.

        • Conference presentation, SIGMETRICS, June 2018.

          • Invited talk at Northeastern University, ECE, Feb. 2018.

            • Invited talk at 1st Workshop on Storage, Control, Networking in Dynamic Systems (SCNDS), co-located with SSS 2017. Nov. 2017.

    • Tolerating Byzantine Adversaries in Distributed Systems

      • Invited talk, Purdue University, CS, April 2017.

        • Invited talk, University of Pittsburgh, ECE, April 2017.

          • Invited talk, Texas A&M University, ECE, April 2017.

            • Invited talk, Theory of Distributed Systems Seminar, MIT, March 2017.

              • Invited talk, New Jersey Institute of Technology, CS. March 2017.

                • Invited talk, Georgia Institute of Technology, ISyE, Feb. 2017.

                • Invited talk, University of Alberta, CS, Feb. 2017.

                • Invited talk, Illinois Institute of Technology, CS. Feb. 2017.

                • Invited talk, University of Illinois at Urbana-Champaign, CS, Jan. 2017.

                • Invited talk, Purdue University, ECE, Jan. 2017.

                • Invited talk, Purdue University, IE, Nov. 2016.

    • Distributed Learning in the Presence of Adversaries

      • Invited talk at INFORMS Annual Meeting, Nov. 2016

    • Asynchronous Non-Bayesian Learning in the Presence of Crash Failures

      • Conference presentation, SSS, Nov 2016

    • Robust Multi-Agent Optimization: Coping with Byzantine Agents with Input Redundancy

      • Conference presentation, SSS, Nov 2016

    • Non-Bayesian learning in the presence of Byzantine agents

      • Conference presentation, DISC, Sept. 2016

        • Invited talk, Zhejiang University, P. R. China, Dec. 2016

    • Fault-tolerant multi-agent optimization: Optimal distributed algorithms

      • Conference presentation, PODC, July 2016

        • Invited talk, Zhejiang University, P. R. China, Dec. 2016

    • Multi-agent optimization in the presence of Byzantine adversaries: Fundamental limits

      • Conference presentation, ACC, July 2016

    • Reaching iterative approximate Byzantine consensus with multi-hop communication

      • SSS, Aug. 2015.

        • The 5th Midwest Workshop in Control and Game Theory}, Purdue University, Apr. 2016.

    • Fault-tolerant optimization in large-scale distributed machine learning

      • Multidisciplinary Research and Data Science Student + Postdoc Workshop, Purdue University, May 2016.