Alexander Tyurin

5

Papers

1

Total Citations

Papers (5)

From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes

2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting

Momentum Provably Improves Error Feedback!