collaborators

5 papers

cs.LG2026

Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration

Alexander Tyurin

Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function va…

cs.LG2026

Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning

Alexander Tyurin, Andrei Spiridonov, Varvara Rudenko

We study distributed reinforcement learning (RL) with policy gradient methods under asynchronous and parallel computations and communications. While non-distributed methods are wel…

math.OC2026

Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction

Alexander Tyurin

We consider centralized distributed optimization in the classical federated learning setup, where workers jointly find an -stationary point of an -smooth, -d…

cs.LG2026

Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD Methods

Alexander Tyurin, Danil Sivtsov

We propose a new unifying framework, Birch SGD, for analyzing and designing distributed SGD methods. The central idea is to represent each method as a weighted directed tree, refer…

cs.LG2026

Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme

Mikhail Persiianov, Jiawei Chen, Petr Mokrov +3

Learning population dynamics involves recovering the underlying process that governs particle evolution, given evolutionary snapshots of samples at discrete time points. Recent met…