Samuel Horvath
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8Can Muon Fine-tune Adam-Pretrained Models?
arXiv 2026
Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning
arXiv 2024
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
arXiv 2024
Vanishing Feature: Diagnosing Model Merging and Beyond
arXiv 2024
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
arXiv 2024
Low-Resource Machine Translation through the Lens of Personalized Federated Learning
arXiv 2024
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
arXiv 2023
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity
arXiv 2022
Affiliations
Frequent co-authors
10from 8 papers