activity
20222026
most citedStochastic Gradient Methods with Preconditioned Updates

2 citations · 2 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2026

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

Abdulla Jasem Almansoori, Maria Ivanova, Andrey Veprikov +3

Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights, dramatically reducing trainable parameters and memory. In this work, we ad…

cs.LG2025

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update

Abdulla Jasem Almansoori, Maria Ivanova, Andrey Veprikov +3

Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights, dramatically reducing trainable parameters and memory. However, there is s…

cs.LG2024

Collaborative and Efficient Personalization with Mixtures of Adaptors

Abdulla Jasem Almansoori, Samuel Horváth, Martin Takáč

Heterogenous data is prevalent in real-world federated learning. We propose a parameter-efficient framework, Federated Low-Rank Adaptive Learning (FLoRAL), that allows clients to p…

cs.LG2023

Byzantine-Tolerant Methods for Distributed Variational Inequalities

Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu +4

Robustness to Byzantine attacks is a necessity for various distributed training scenarios. When the training reduces to the process of solving a minimization problem, Byzantine rob…

cs.CV2022

PaDPaF: Partial Disentanglement with Partially-Federated GANs

Abdulla Jasem Almansoori, Samuel Horváth, Martin Takáč

Federated learning has become a popular machine learning paradigm with many potential real-life applications, including recommendation systems, the Internet of Things (IoT), health…

math.OC2022★ 2 cited

Stochastic Gradient Methods with Preconditioned Updates

Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori +3

This work considers the non-convex finite sum minimization problem. There are several algorithms for such problems, but existing methods often work poorly when the problem is badly…