Peter Richtarik
The First Optimal Parallel SGD (in the Presence of Data, Compute and Communication Heterogeneity)
Watch keynote
PDF

Francesco Orabona
Understanding Adam and AdamW through Proximal Updates, Scale-Freeness, and Relaxed Smoothness
Watch keynote
PDF

Martin Takac
Elevating Federated Learning: A Shift Towards Second-Order Optimization Methods
Watch keynote
PDF

Alexander Beznosikov
Navigating Byzantine Attacks in Distributed Learning: a Trial Function Methodology
Watch keynote
PDF

Alexey Naumov
Stochastic approximation: old and new
Watch keynote
PDF

Andrey Kuznetsov
Multimodal architectures and context compression methods (online)
Watch keynote
PDF

Boris Mordukhovich
Convergence of Descent Methods under Polyak-Kurdyka-Lojasiewicz Properties (online)
Watch keynote
PDF

Vladimir Spokoiny
Inference for nonlinear inverse problems
Watch keynote
PDF

Gesualdo Scutari
Bringing Statistical Thinking in Decentralized Optimization. Vignettes from High-dimensional Statistics over Networks (online)
Watch keynote

Alexander Gasnikov
Survey of modern results in gradient-free convex optimization
Watch keynote
PDF

Roland Hildebrand
Geometric view-points on barrier functions as driver of recent and future progress
Watch keynote
PDF

Evgeny Burnaev
Adversarial Schrödinger Bridge Matching for Fast Generative Modeling
Watch keynote
PDF

Ivan Oseledets
Effective tensor and matrix methods in deep learning
Watch keynote
PDF

Vladimir Temlyakov
Some remarks on optimization on Banach spaces
Watch keynote
PDF

Dmitry Yarotsky
SGD with memory: fundamental properties and stochastic acceleration
Watch keynote
PDF

Denis Dimitrov
Diffusion (and more) text-to-video generation methods
Watch keynote
PDF

Andrey Vorobyev
Optimization problems for analog devices linearization in wireless communication systems
Watch keynote

Evgeny Tyrtyshnikov
Optimization and tensor decompositions
Watch keynote
PDF