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