Andrey Veprikov

Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order LLM Fine-Tuning

Aligning Distributionally Robust Optimization with Practical Deep Learning Needs

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods

Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics

SimplexLoRA: Dynamic Rank Updating via Alternating Minimization with Simplex Projection

Markovian Compression: Looking to the Past Helps Accelerate the Future