Andrey Veprikov

Orcid: 0009-0001-9126-572X

According to our database1, Andrey Veprikov authored at least 12 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC.
CoRR, February, 2026

Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling.
CoRR, February, 2026

Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers.
CoRR, February, 2026

Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
A mathematical model of the hidden feedback loop effect in machine learning systems.
Knowl. Inf. Syst., December, 2025

DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning.
CoRR, November, 2025

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods.
CoRR, October, 2025

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update.
CoRR, September, 2025

Aligning Distributionally Robust Optimization with Practical Deep Learning Needs.
CoRR, August, 2025

Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order.
CoRR, June, 2025

WeightLoRA: Keep Only Necessary Adapters.
CoRR, June, 2025

2024
A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems.
CoRR, 2024


  Loading...