Talks and Poster Presentations

Future Talks

15. Workshop on Optimization for Machine Learning (NeurIPS 2024)

    Vancouver, Canada
    Vancouver Convention Center

    December 15, 2024
    Presenting
    • MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times (Oral )
    • Differentially Private Random Block Coordinate Descent
    • LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
16. MLR Weekly Seminar

    Online
    Machine Learning Research at Apple

    November 21, 2024
    Invited by Samy Bengio to give a talk on MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times

2024 Talks and Poster Presentations

13. Interntional Conference on Algebra, Logic, and their Applications

    Online
    Yerevan State University

    October 18, 2024
    Delivered a talk on MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
14. CEMSE E-Poster Competition

    KAUST, Saudi Arabia
    KAUST

    October 10, 2024
    Presented a poster on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [3rd place]
15. Analysis, PDEs and Applications

    Yerevan, Armenia
    Yerevan State University

    July 6, 2024
    Delivered a talk on MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times [abstract]
16. Stochastic Numerics and Statistical Learning

    KAUST, Saudi Arabia
    KAUST

    May 27, 2024
    Presented a poster on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [poster]
17. CS 331, Stochastic Gradient Descent Methods

    KAUST, Saudi Arabia
    KAUST

    May 5, 2024
    Delivered a guest lecture on MindFlayer: Efficient Asynchronous Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
18. The Machine Learning Summer School in Okinawa 2024

    Okinawa, Japan
    Okinawa Institute of Science and Technology (OIST)

    March 13, 2024
    Presented a poster on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [poster]
19. KAUST Rising Stars in AI Symposium 2024

    KAUST, Saudi Arabia
    KAUST

    February 21, 2024
    Presented a poster on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [poster]

2023 Talks and Poster Presentations

6. Group Seminar

   KAUST, Saudi Arabia
   KAUST

   November 16, 2023
   Delivered a talk on Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
7. Algorithms & Computationally Intensive Inference seminars

   Coventry, England
   University of Warwick

   October 6, 2023
   Delivered a talk on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [slides]
8. Mathematics in Armenia: Advances and Perspectives

   Yerevan, Armenia
   Yerevan State University

   July 5, 2023
   Delivered a talk on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [abstract]
9. Machine Learning Reading Group Yerevan

   Yerevan, Armenia
   Yerevan State University

   March 10, 2023
   Delivered a talk on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [video (Armenian)]

2022 Talks and Poster Presentations

2. Federated Learning One World Seminar (FLOW)

   Online
   Online

   December 7, 2022
   Delivered a talk on GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity [video]
3. Machine Learning Reading Group Yerevan

   Yerevan, Armenia
   Yerevan State University

   April 10, 2022
   Delivered a talk on ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!