Talks · Video Talks

1. From the Broximal Point Method to Efficient Training of LLMs (start: 8:50)
   Workshop on Learning from Heterogeneous Sources, Simons Institute, 2/2026
2. Tutorial: Federated Optimization, Part I (72 mins)
   Federated and Collaborative Learning Boot Camp, Simons Institute, 1/2026
3. Tutorial: Federated Optimization, Part II (72 mins)
   Federated and Collaborative Learning Boot Camp, Simons Institute, 1/2026
4. Tutorial: Federated Optimization, Part III (65 mins)
   Federated and Collaborative Learning Boot Camp, Simons Institute, 1/2026
5. The First Optimal Parallel SGD
   Federated Learning One World Seminar, 4/2025
6. The role of local training in federated learning (90 mins)
   Better AI Meetup, Bratislava, Slovakia, 6/2022
7. ProxSkip: Yes! Local gradient steps provably lead to communication acceleration! Finally! (71 mins)
   Federated Learning One World Seminar, 5/2022
8. Permutation compressors for provably faster distributed nonconvex optimization (5 mins)
   ICLR video talk, 3/2022
9. Permutation compressors for provably faster distributed nonconvex optimization (78 mins)
   Federated Learning One World Seminar, 2/2022
10. Permutation compressors for provably faster distributed nonconvex optimization (67 mins)
    Machine Learning NeEDS Mathematical Optimization, 2/2022
11. EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback (62 mins)
    Federated Learning One World Seminar, 7/2021
12. Beyond Local and Gradient Methods for Federated Learning (80 mins)
    Federated Learning One World Seminar, 4/2021
13. Distributed Second Order Methods with Fast Rates and Compressed Communication
    All Russian Optimization Seminar, 4/2021
14. On Second Order Methods and Randomness (72 mins)
    Montreal MLOpt Seminar, 5/2020
15. On Second Order Methods and Randomness (73 mins)
    One World Optimization Seminar, 4/2020
16. A Guided Walk Through the ZOO of Stochastic Gradient Descent Methods (5 hrs)
    MIPT, Moscow, Russia, 9/2019
17. Variance Reduction for Gradient Compression (38 mins)
    Rutgers University, 9/2019
18. Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching (33 mins)
    Simons Institute, Berkeley, 9/2018
19. SGD: General Analysis and Improved Rates (start: 35:40 end: 53:11)
    ICML 2019
20. Empirical Risk Minimization: Complexity, Duality, Sampling, Sparsity and Big Data (85 mins)
    Yandex, Russia, 12/2017
21. Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling (1 hr)
    MIPT, Moscow, Russia, 10/2017
22. Introduction to Randomized Optimization 1 2 3 4 5 (5 hrs)
    Ecole Polytechnique, France, 8/2017
23. Stochastic Dual Ascent for Solving Linear Systems (31 mins)
    The Alan Turing Institute, London, UK, 10/2016
24. Introduction to Big Data Optimization (55 mins)
    Portsmouth, UK, 9/2016
25. Accelerated, Parallel and Proximal Coordinate Descent (90 mins)
    Moscow, Russia, 2/2014
26. Parallel Coordinate Descent Methods for Big Data Optimization (55 mins)
    Simons Institute, Berkeley, 10/2013